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 24576
    5. 8-RES_FS24576-JB
    6. 23320
    Prev
    Next
    INDEX
    Explanations

    phrases related to policy revisions and accountability measures

    oai_token-act-pair · gpt-4o-miniTriggered 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
    87
    +0.38
    2.0%
    756
    +0.15
    0.8%
    409
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.38
    -0.02
    756
    +0.15
    -0.01
    665
    +0.11
    0.07
    Negative Logits
    toggle
    -0.69
     Babe
    -0.66
    ampire
    -0.58
    nikov
    -0.57
     smelled
    -0.57
    joy
    -0.55
     Valentine
    -0.55
    inho
    -0.55
     Didn
    -0.55
     frontman
    -0.55
    POSITIVE LOGITS
    .''.
    0.94
    .�
    0.86
    .</
    0.84
     future
    0.84
    .''
    0.83
     appropriate
    0.81
     stakeholders
    0.79
    .","
    0.78
    )."
    0.78
     mutually
    0.78
    Activations Density 1.039%

    No Known Activations