© 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. 45821
    Prev
    Next
    INDEX
    Explanations

    legal and crime-related terms and descriptions

    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%
    241
    +0.12
    0.6%
    310
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.13
    0.08
    430
    +0.12
    0.13
    677
    +0.11
    0.08
    Negative Logits
    igham
    -0.68
    igans
    -0.67
    udeb
    -0.57
    abby
    -0.54
    aghetti
    -0.53
    ctors
    -0.53
    utf
    -0.53
     hygiene
    -0.51
    udging
    -0.51
    ucci
    -0.51
    POSITIVE LOGITS
    rd
    0.98
    th
    0.97
    nd
    0.75
    ths
    0.73
    TH
    0.69
    2200
    0.68
     Madness
    0.67
    âĢ³
    0.67
     anniversary
    0.65
    ember
    0.65
    Activations Density 6.021%

    No Known Activations