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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12178
    Prev
    Next
    INDEX
    Explanations

    references to the name "Rouse" and "Rousseff"

    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
    326
    +0.10
    0.5%
    481
    +0.09
    0.4%
    366
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.01
    366
    +0.09
    0.01
    466
    +0.09
    0.01
    Negative Logits
    ulhu
    -0.74
    DCS
    -0.72
    asper
    -0.68
     PowerPoint
    -0.68
     Grateful
    -0.67
    lishes
    -0.66
    NPR
    -0.64
    APS
    -0.62
    PsyNetMessage
    -0.61
    imately
    -0.60
    POSITIVE LOGITS
    bra
    1.00
    ments
    0.88
    y
    0.87
    te
    0.83
    ¶
    0.83
    stal
    0.83
    hyde
    0.82
    mania
    0.81
    lli
    0.81
    ¼
    0.80
    Activations Density 0.007%

    No Known Activations