© 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. 39943
    Prev
    Next
    INDEX
    Explanations

    words related to legal cases and 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
    120
    +0.09
    0.5%
    289
    +0.08
    0.5%
    343
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.18
    326
    +0.08
    0.18
    285
    +0.08
    0.04
    Negative Logits
     anten
    -0.63
    ¿½
    -0.53
     Shack
    -0.52
     Arm
    -0.49
     Jacket
    -0.48
     Village
    -0.47
     mosqu
    -0.46
     Boots
    -0.46
    Arm
    -0.45
     Generation
    -0.45
    POSITIVE LOGITS
     cas
    0.76
     caster
    0.73
    hew
    0.73
    etime
    0.72
    emate
    0.70
    ework
    0.66
    hews
    0.64
    eless
    0.61
    estro
    0.60
    icter
    0.60
    Activations Density 5.661%

    No Known Activations