© 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. 13643
    Prev
    Next
    INDEX
    Explanations

    statistics, particularly related to sports performance

    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
    323
    +0.09
    0.4%
    174
    +0.08
    0.4%
    176
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.09
    0.22
    176
    +0.08
    0.07
    314
    +0.08
    -0.05
    Negative Logits
    cens
    -0.73
    may
    -0.70
    enegger
    -0.69
    esson
    -0.68
     aisle
    -0.67
    thouse
    -0.66
    tin
    -0.65
    wcsstore
    -0.64
    opol
    -0.63
    nant
    -0.63
    POSITIVE LOGITS
     Ratio
    0.82
    BIP
    0.73
     destro
    0.70
     Skills
    0.69
     STATS
    0.69
     ratio
    0.69
     Stats
    0.68
     Blazers
    0.66
    ccording
    0.66
     cryst
    0.65
    Activations Density 8.545%

    No Known Activations