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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 1770
    Prev
    Next
    INDEX
    Explanations

    legal case references and related terms

    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
    31
    +0.09
    0.4%
    607
    +0.09
    0.4%
    348
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.09
    0.05
    651
    +0.09
    0.04
    370
    +0.09
    0.04
    Negative Logits
     livest
    -0.80
    pees
    -0.78
    attery
    -0.72
    ower
    -0.71
    urous
    -0.70
    resent
    -0.69
    reath
    -0.69
    emouth
    -0.68
    inges
    -0.68
    atomic
    -0.67
    POSITIVE LOGITS
    cases
    0.95
     involving
    0.80
    esan
    0.76
     Keen
    0.75
    case
    0.74
    cmp
    0.72
    backs
    0.67
    finding
    0.67
    suit
    0.66
    making
    0.66
    Activations Density 0.431%

    No Known Activations