© 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 Local
    9. 6-RES_SCL-AJT
    11. 31879
    Prev
    Next
    INDEX
    Explanations

    mentions of legal terms, criminal activities, and judicial processes

    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
    +0.23
    1.1%
    288
    +0.10
    0.5%
    7
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    643
    +0.23
    0.04
    697
    +0.10
    0.05
    134
    +0.09
    0.07
    Negative Logits
    aven
    -0.67
    gm
    -0.66
    mentation
    -0.65
    hare
    -0.65
    arity
    -0.63
    orns
    -0.63
    eah
    -0.62
    ankind
    -0.61
    alle
    -0.60
    ophe
    -0.60
    POSITIVE LOGITS
     felon
    0.90
    icts
    0.76
     guilty
    0.72
     convict
    0.70
     perjury
    0.69
    rupt
    0.66
     unfocusedRange
    0.65
     fel
    0.65
    eering
    0.64
    icted
    0.63
    Activations Density 9.557%

    No Known Activations