© 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. 10546
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to legal proceedings

    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
    416
    +0.11
    0.5%
    1
    +0.09
    0.4%
    668
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.11
    0.12
    527
    +0.09
    0.07
    134
    +0.09
    0.10
    Negative Logits
    ablishment
    -0.81
    soType
    -0.80
    é¾įå¥ij士
    -0.73
     governing
    -0.72
     Canaver
    -0.69
    Effective
    -0.68
    idelines
    -0.68
     regulating
    -0.67
     awarding
    -0.66
    VERTIS
    -0.66
    POSITIVE LOGITS
     disappeared
    0.97
     suffered
    0.89
     escaped
    0.88
     survived
    0.86
     vanished
    0.83
     suffers
    0.82
     migrated
    0.81
     langu
    0.76
     bounced
    0.76
     missing
    0.74
    Activations Density 5.685%

    No Known Activations