© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 43124
    Prev
    Next
    INDEX
    Explanations

    references to government actions and security-related issues

    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
    87
    +0.29
    1.4%
    447
    +0.11
    0.5%
    346
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.29
    0.07
    146
    +0.11
    0.06
    346
    +0.09
    0.06
    Negative Logits
    selves
    -0.61
    ————————————————
    -0.61
    $.
    -0.57
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.54
    âĶĢâĶĢâĶĢâĶĢ
    -0.54
    ocamp
    -0.53
    achment
    -0.53
    Lear
    -0.53
    range
    -0.53
    ãĤ¤ãĥĪ
    -0.53
    POSITIVE LOGITS
     meanwhile
    1.20
     intervened
    1.09
     reacted
    1.07
     responded
    0.94
     applauded
    0.93
     congratulated
    0.89
     appealed
    0.88
     however
    0.88
     countered
    0.87
     alerted
    0.86
    Activations Density 0.385%

    No Known Activations