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. 43255
    Prev
    Next
    INDEX
    Explanations

    funding sources and organizations related to scientific research

    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
    317
    +0.12
    0.5%
    292
    +0.10
    0.5%
    306
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.12
    0.02
    317
    +0.10
    0.02
    680
    +0.10
    0.01
    Negative Logits
    paio
    -0.79
    ghazi
    -0.73
     brut
    -0.72
    killers
    -0.72
     confuse
    -0.71
     killers
    -0.71
    ophobic
    -0.71
     whine
    -0.70
    xual
    -0.70
    aviour
    -0.70
    POSITIVE LOGITS
     grant
    1.17
     grants
    1.12
     NIH
    1.09
     concess
    1.08
     Grants
    1.02
    Grant
    0.99
     Fellowship
    0.99
     scholarships
    0.97
     Funding
    0.95
     scholarship
    0.93
    Activations Density 0.083%

    No Known Activations