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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26317
    Prev
    Next
    INDEX
    Explanations

    continuous actions or processes described in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    581
    +0.10
    0.4%
    431
    +0.09
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    431
    +0.10
    0.03
    713
    +0.09
    0.02
    341
    +0.09
    0.03
    Negative Logits
     manag
    -0.69
    cop
    -0.68
    =-=-
    -0.64
    ikers
    -0.64
     kicker
    -0.62
     laun
    -0.60
    reet
    -0.60
    cknowled
    -0.58
    ritical
    -0.58
     WTO
    -0.58
    POSITIVE LOGITS
     tonight
    0.84
    hani
    0.80
     lately
    0.75
     today
    0.74
    piring
    0.72
    soDeliveryDate
    0.71
    utical
    0.70
    Ø©
    0.70
    igating
    0.70
    edIn
    0.69
    Activations Density 0.071%

    No Known Activations