© 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. 45823
    Prev
    Next
    INDEX
    Explanations

    mentions of legal terms and court-related activities

    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
    +0.17
    0.7%
    7
    +0.16
    0.7%
    414
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.17
    0.19
    430
    +0.16
    0.16
    224
    +0.15
    0.10
    Negative Logits
    haar
    -0.90
    ohyd
    -0.86
    rolet
    -0.85
    orne
    -0.84
     Rivals
    -0.84
     Roads
    -0.81
    kefeller
    -0.79
    irst
    -0.78
    ulus
    -0.78
    irth
    -0.78
    POSITIVE LOGITS
     presiding
    1.07
    rooms
    0.98
     overseeing
    0.97
     Advocate
    0.95
     rulings
    0.84
     ruled
    0.84
     Gorsuch
    0.80
    room
    0.80
    jud
    0.79
     unfocusedRange
    0.78
    Activations Density 7.912%

    No Known Activations