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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 2482
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and players

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    288
    +0.13
    0.6%
    457
    +0.11
    0.5%
    739
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.12
    409
    +0.11
    0.05
    343
    +0.10
    0.06
    Negative Logits
    nces
    -0.89
    mble
    -0.88
    aeda
    -0.88
    abases
    -0.82
    erva
    -0.80
    irin
    -0.79
    HER
    -0.77
    yip
    -0.75
    eeper
    -0.73
    warm
    -0.72
    POSITIVE LOGITS
    omatic
    0.90
    shire
    0.75
    otomy
    0.68
    dale
    0.67
    exec
    0.67
    immune
    0.67
    ufact
    0.66
    owa
    0.65
    obil
    0.65
    auga
    0.65
    Activations Density 1.149%

    No Known Activations