© 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. 34762
    Prev
    Next
    INDEX
    Explanations

    mentions related to awards, rewards, recognition, and achievements

    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
    +0.30
    1.5%
    481
    +0.13
    0.6%
    408
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.30
    0.20
    362
    +0.13
    0.15
    562
    +0.11
    0.10
    Negative Logits
    orthy
    -0.80
    redits
    -0.79
    ÄŁ
    -0.77
    atu
    -0.70
    onis
    -0.69
    ometers
    -0.69
    utics
    -0.68
    OIL
    -0.68
    matter
    -0.67
    Specific
    -0.66
    POSITIVE LOGITS
     beast
    0.73
     saga
    0.68
     Prometheus
    0.67
     Frenchman
    0.67
     notion
    0.67
     rainbow
    0.66
     moniker
    0.66
     trio
    0.66
     acronym
    0.66
     duo
    0.65
    Activations Density 12.642%

    No Known Activations