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 6144
    5. 8-RES_FS6144-JB
    6. 5471
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical malfunctions and resolutions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    737
    +0.11
    0.5%
    432
    +0.10
    0.5%
    225
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    674
    +0.11
    0.05
    284
    +0.10
    0.05
    396
    +0.10
    0.04
    Negative Logits
    ARA
    -0.87
     Publications
    -0.82
     Camer
    -0.78
     Mech
    -0.77
     Petersen
    -0.74
    enhagen
    -0.72
    Camp
    -0.71
    endars
    -0.69
    Audio
    -0.69
    Camera
    -0.69
    POSITIVE LOGITS
     weak
    0.99
     indifferent
    0.97
     rotten
    0.96
     imperfect
    0.95
     overpowered
    0.95
     unhealthy
    0.93
     moderately
    0.93
     deficient
    0.93
     unrem
    0.93
     insignificant
    0.92
    Activations Density 1.128%

    No Known Activations