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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5284
    Prev
    Next
    INDEX
    Explanations

    texts related to legal and criminal activities

    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
    697
    +0.12
    0.5%
    496
    +0.10
    0.4%
    675
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.12
    0.16
    48
    +0.10
    0.12
    650
    +0.10
    0.13
    Negative Logits
     unborn
    -0.84
     clitor
    -0.79
     metic
    -0.71
     flowering
    -0.71
     bount
    -0.69
     interns
    -0.69
     fundament
    -0.69
     vacation
    -0.68
     oppressed
    -0.68
     extrater
    -0.68
    POSITIVE LOGITS
    Likewise
    0.99
    ï¸ı
    0.98
    âĶĢâĶĢ
    0.97
    Because
    0.95
    Additionally
    0.94
     Similarly
    0.94
    ----------------------------------------------------------------
    0.93
    However
    0.93
    Moreover
    0.92
    Certainly
    0.91
    Activations Density 1.070%

    No Known Activations