© 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 EvalsExportsAPI 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. 6214
    Prev
    Next
    INDEX
    Explanations

    mentions of specific countries and geopolitical situations, especially in the Middle East

    oai_token-act-pair · gpt-3.5-turbo
    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
    393
    +0.36
    1.4%
    376
    +0.16
    0.6%
    595
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.36
    0.13
    0
    +0.16
    0.11
    595
    +0.13
    0.09
    Negative Logits
    nea
    -0.89
    tera
    -0.87
    xia
    -0.85
    :(
    -0.84
    yang
    -0.83
    .*
    -0.83
    hao
    -0.81
    ixel
    -0.81
    elle
    -0.80
    hyde
    -0.79
    POSITIVE LOGITS
     assorted
    1.38
     etc
    1.33
    etc
    1.26
     possibly
    1.08
     others
    1.06
     other
    0.89
     redistributed
    0.82
     perhaps
    0.79
     surroundings
    0.78
     consequently
    0.76
    Activations Density 2.573%

    No Known Activations