© 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. 11246
    Prev
    Next
    INDEX
    Explanations

    database table operations and technical instructions containing specific identifiers and commands

    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
    +0.11
    0.5%
    269
    +0.11
    0.5%
    60
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.11
    0.06
    314
    +0.11
    0.01
    639
    +0.10
    0.06
    Negative Logits
     stakes
    -0.71
    Merit
    -0.69
     seriousness
    -0.68
     handlers
    -0.67
     rolls
    -0.67
     steadfast
    -0.66
     bitterly
    -0.66
     integrity
    -0.66
     Integrity
    -0.63
     handler
    -0.63
    POSITIVE LOGITS
    cess
    1.07
    lator
    1.03
    kered
    1.01
    portation
    1.00
    formation
    0.99
    ciation
    0.96
    ference
    0.94
    itional
    0.93
    FTWARE
    0.92
    lation
    0.89
    Activations Density 1.011%

    No Known Activations