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. 46062
    Prev
    Next
    INDEX
    Explanations

    phrases indicating self-identification and personal labels

    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
    +0.13
    0.6%
    541
    +0.09
    0.4%
    362
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.13
    0.03
    36
    +0.09
    0.03
    327
    +0.09
    0.02
    Negative Logits
    iasco
    -0.82
    ptoms
    -0.80
     delays
    -0.75
    glers
    -0.72
     ponds
    -0.69
    trap
    -0.69
     deaths
    -0.68
    ousse
    -0.67
     spills
    -0.67
     flights
    -0.66
    POSITIVE LOGITS
     libertarian
    0.92
     nonpartisan
    0.87
    ĪĴ
    0.86
     Libertarian
    0.80
     unbiased
    0.80
     progressive
    0.79
     fearless
    0.78
     centrist
    0.78
     principled
    0.78
     pacif
    0.78
    Activations Density 0.079%

    No Known Activations