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. 1796
    Prev
    Next
    INDEX
    Explanations

    requests or calls to take specific actions related to safety or technology

    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
    447
    +0.14
    0.6%
    410
    +0.12
    0.6%
    177
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.14
    0.09
    30
    +0.12
    0.06
    346
    +0.11
    0.10
    Negative Logits
    venge
    -0.77
    NULL
    -0.72
    abiding
    -0.68
    iencies
    -0.66
    ctrl
    -0.66
     perimeter
    -0.65
    addons
    -0.64
     backbone
    -0.63
    KS
    -0.62
    ATER
    -0.62
    POSITIVE LOGITS
     quoted
    1.18
     remarked
    1.11
     proverb
    1.05
     aptly
    1.02
     commented
    1.02
     famously
    0.99
     Economist
    0.98
     reviewer
    0.98
     commentator
    0.97
     lamented
    0.95
    Activations Density 2.614%

    No Known Activations