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 24576
    5. 8-RES_FS24576-JB
    6. 23207
    Prev
    Next
    INDEX
    Explanations

    specific technical components, specifications, or features related to products and systems

    oai_token-act-pair · gpt-4o-miniTriggered 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
    87
    +0.18
    0.9%
    578
    +0.13
    0.6%
    756
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.18
    0.09
    537
    +0.13
    0.07
    225
    +0.12
    0.07
    Negative Logits
    à¨
    -0.63
    talk
    -0.58
    ier
    -0.57
    stream
    -0.56
    Lear
    -0.56
    xious
    -0.56
    ivably
    -0.56
    lly
    -0.55
    istical
    -0.55
    lier
    -0.54
    POSITIVE LOGITS
    hip
    1.21
    hips
    1.13
    cape
    1.13
    pring
    1.11
    heet
    1.10
    mith
    1.09
    etter
    1.09
    cale
    1.09
    uggest
    1.02
    hirt
    1.01
    Activations Density 0.506%

    No Known Activations