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. 45883
    Prev
    Next
    INDEX
    Explanations

    high-frequency terms or articles 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
    481
    +0.21
    1.0%
    640
    +0.18
    0.9%
    393
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.21
    0.06
    393
    +0.18
    0.05
    159
    +0.17
    0.04
    Negative Logits
    thood
    -0.83
    perse
    -0.78
    ����
    -0.76
    ashington
    -0.74
    leground
    -0.73
    Scotland
    -0.71
    minent
    -0.70
    angering
    -0.70
    uclear
    -0.69
    20439
    -0.68
    POSITIVE LOGITS
     downside
    1.30
    oret
    1.27
     biggest
    1.16
     drawback
    1.11
     sheer
    1.08
     easiest
    1.06
     simplest
    1.05
     coolest
    1.00
     latter
    0.99
     cheapest
    0.98
    Activations Density 0.206%

    No Known Activations