© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 7283
    Prev
    Next
    INDEX
    Explanations

    information related to sports leagues, teams, and victories

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    183
    +0.10
    0.5%
    7
    +0.09
    0.4%
    606
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.10
    0.04
    183
    +0.09
    0.04
    603
    +0.09
    0.03
    Negative Logits
    senal
    -0.67
    tan
    -0.65
    heter
    -0.63
     scanner
    -0.62
    tar
    -0.59
     sket
    -0.59
    opter
    -0.59
    ria
    -0.57
    erous
    -0.57
     protr
    -0.56
    POSITIVE LOGITS
    't
    0.98
    nings
    0.88
     championships
    0.85
     outright
    0.85
     streak
    0.84
    ced
    0.82
     streaks
    0.82
     decisively
    0.78
    cest
    0.76
    throp
    0.76
    Activations Density 0.052%

    No Known Activations