© 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. 39965
    Prev
    Next
    INDEX
    Explanations

    sports-related rankings and player mentions in the context of competitive sports leagues

    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
    +0.18
    0.9%
    67
    +0.10
    0.5%
    649
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.18
    0.21
    709
    +0.10
    0.13
    609
    +0.09
    0.11
    Negative Logits
    acet
    -0.72
    uala
    -0.63
    igham
    -0.63
    ruce
    -0.62
    joy
    -0.61
    elcome
    -0.60
     Hik
    -0.59
    ington
    -0.59
    walking
    -0.58
    bring
    -0.57
    POSITIVE LOGITS
    %:
    0.86
     contenders
    0.78
    %,
    0.75
     earners
    0.74
    %.
    0.72
    nings
    0.71
     rankings
    0.69
     tiers
    0.68
     ranking
    0.66
    %;
    0.66
    Activations Density 9.080%

    No Known Activations