© 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 Local
    9. 6-RES_SCL-AJT
    11. 45754
    Prev
    Next
    INDEX
    Explanations

    historical and legal terms related to government actions or legal proceedings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.13
    0.6%
    611
    +0.12
    0.6%
    746
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.21
    611
    +0.12
    0.13
    4
    +0.11
    0.09
    Negative Logits
    izont
    -0.81
    isha
    -0.68
     foremost
    -0.67
     contrace
    -0.67
     traveller
    -0.67
    jew
    -0.64
    bnb
    -0.64
    asha
    -0.63
    keepers
    -0.62
    ishi
    -0.62
    POSITIVE LOGITS
    umbnail
    0.90
    ragon
    0.89
    vous
    0.83
    ures
    0.78
    e
    0.77
    urally
    0.75
    uits
    0.73
    ez
    0.72
    ornia
    0.72
    olls
    0.72
    Activations Density 8.445%

    No Known Activations