© 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. 34821
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases, criminal activity, and incidents involving law enforcement

    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
    +0.15
    0.6%
    575
    +0.12
    0.5%
    550
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.15
    0.20
    575
    +0.12
    0.21
    383
    +0.11
    0.14
    Negative Logits
    avorite
    -0.73
    hem
    -0.67
     ank
    -0.66
    irie
    -0.65
    uctions
    -0.65
     bluff
    -0.64
    ortium
    -0.64
     moreover
    -0.64
    eness
    -0.62
    warts
    -0.61
    POSITIVE LOGITS
    abouts
    0.89
    EStream
    0.80
    bell
    0.77
    frames
    0.76
    ZI
    0.73
     sidx
    0.72
     frame
    0.70
    isch
    0.70
    liest
    0.69
    GHz
    0.68
    Activations Density 11.136%

    No Known Activations