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

    Neuronpedia

    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. 3529
    Prev
    Next
    INDEX
    Explanations

    references to labels, specifically within coding contexts

    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
    288
    +0.18
    0.6%
    274
    +0.14
    0.5%
    526
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.06
    326
    +0.14
    0.05
    274
    +0.14
    0.04
    Negative Logits
    ashington
    -0.93
    tein
    -0.91
    hire
    -0.90
    enty
    -0.87
    vati
    -0.86
     odds
    -0.85
    issance
    -0.85
    gm
    -0.84
    atana
    -0.84
    uld
    -0.83
    POSITIVE LOGITS
     labels
    1.02
     label
    1.00
    strip
    0.97
    mates
    0.96
    cloth
    0.95
    mate
    0.95
    escent
    0.92
    ovo
    0.91
    BIL
    0.90
    Matrix
    0.90
    Activations Density 0.754%

    No Known Activations