© 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. 8526
    Prev
    Next
    INDEX
    Explanations

    programming code snippets related to adding constraints and checking numerical values

    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
    706
    +0.07
    0.5%
    120
    +0.07
    0.5%
    690
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.07
    0.02
    366
    +0.07
    0.02
    26
    +0.07
    0.02
    Negative Logits
    ãģ®æ
    -0.51
    ONES
    -0.50
    ostics
    -0.49
    ãģ®å
    -0.49
    è£ħ
    -0.47
     GOODMAN
    -0.47
    lessly
    -0.47
    oned
    -0.45
    istle
    -0.44
    icken
    -0.44
    POSITIVE LOGITS
    ball
    0.63
    profits
    0.56
    fit
    0.55
    BALL
    0.52
    balls
    0.49
    minster
    0.48
    cer
    0.48
    profit
    0.46
    fitting
    0.45
    ws
    0.45
    Activations Density 0.060%

    No Known Activations