Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45265
    Prev
    Next
    INDEX
    Explanations

    references to basketball players, specifically Kobe Bryant, and discussions related to basketball

    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
    618
    +0.12
    0.6%
    57
    +0.12
    0.5%
    343
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.26
    288
    +0.12
    0.28
    709
    +0.12
    0.15
    Negative Logits
    ablishment
    -0.90
    anooga
    -0.90
    apore
    -0.86
    essee
    -0.83
    alez
    -0.78
    rance
    -0.78
    idable
    -0.76
    ereo
    -0.74
    ÃįÃį
    -0.74
    ledge
    -0.73
    POSITIVE LOGITS
     Bryant
    0.97
     Kobe
    0.77
    pered
    0.72
    aths
    0.71
     Ronaldo
    0.70
     Lakers
    0.70
    è£ħ
    0.69
    olson
    0.69
    iscopal
    0.69
    acca
    0.69
    Activations Density 9.155%

    No Known Activations