© 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. 2628
    Prev
    Next
    INDEX
    Explanations

    visual content such as videos and images

    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
    91
    +0.07
    0.5%
    304
    +0.07
    0.5%
    396
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    358
    +0.07
    0.02
    503
    +0.07
    0.02
    27
    +0.06
    0.02
    Negative Logits
    uries
    -0.54
    isine
    -0.54
    metics
    -0.54
    utics
    -0.52
    stasy
    -0.51
     Flavoring
    -0.49
    omics
    -0.49
    cius
    -0.49
    eca
    -0.49
    ounds
    -0.49
    POSITIVE LOGITS
     confir
    0.52
     voic
    0.48
     prosec
    0.45
     lik
    0.44
     happ
    0.43
     explan
    0.43
     conclud
    0.42
     chim
    0.42
     reluct
    0.42
     deploy
    0.42
    Activations Density 0.079%

    No Known Activations