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. 12137
    Prev
    Next
    INDEX
    Explanations

    references to sports events or matches and their outcomes

    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
    481
    +0.13
    0.6%
    570
    +0.11
    0.5%
    378
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    652
    +0.13
    0.04
    281
    +0.11
    0.04
    415
    +0.10
    0.04
    Negative Logits
    ielding
    -0.81
    utterstock
    -0.81
     wield
    -0.65
     adherents
    -0.62
     embattled
    -0.61
     ens
    -0.61
     awaits
    -0.61
     urges
    -0.60
     embodiments
    -0.60
     contends
    -0.59
    POSITIVE LOGITS
     ['
    1.14
     ..."
    1.11
     [
    1.08
     â̦"
    1.01
    )."
    0.96
    ),"
    0.92
    ..."
    0.91
    â̦"
    0.89
    )",
    0.82
    .""
    0.81
    Activations Density 0.562%

    No Known Activations