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 24576
    5. 8-RES_FS24576-JB
    6. 8347
    Prev
    Next
    INDEX
    Explanations

    information related to technology, patent disputes, and legal issues

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    373
    +0.23
    1.1%
    640
    +0.20
    0.9%
    228
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.12
    94
    +0.20
    0.10
    591
    +0.09
    0.08
    Negative Logits
    heit
    -0.88
    burn
    -0.61
     favorably
    -0.60
     hydra
    -0.60
    uno
    -0.60
    aeda
    -0.58
    reetings
    -0.58
    advertisement
    -0.58
     favoring
    -0.58
    hemoth
    -0.58
    POSITIVE LOGITS
    Scroll
    1.06
     Inqu
    0.78
    However
    0.76
     Trafford
    0.72
    Shape
    0.72
    Labour
    0.72
    PHOTOS
    0.72
    VIDEO
    0.69
     Universities
    0.69
     Smy
    0.67
    Activations Density 0.324%

    No Known Activations