© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 11017
    Prev
    Next
    INDEX
    Explanations

    references to political and security-related topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating exclusion or isolation, often involving the term "no-man" or related to "no-fly" zones

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    102
    +0.07
    0.5%
    239
    +0.07
    0.5%
    323
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    614
    +0.07
    0.01
    354
    +0.07
    0.02
    737
    +0.06
    0.02
    Negative Logits
    eways
    -0.50
    itudes
    -0.49
    eworks
    -0.49
    versely
    -0.46
    iven
    -0.46
    atives
    -0.46
    isms
    -0.46
    izations
    -0.45
    osion
    -0.44
    versions
    -0.43
    POSITIVE LOGITS
     Citiz
    0.40
    #$
    0.40
     spot
    0.38
    grab
    0.38
     dab
    0.37
     tested
    0.37
     cann
    0.36
     spared
    0.36
     distingu
    0.36
    paced
    0.36
    Activations Density 0.093%

    No Known Activations