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

    Neuronpedia

    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. 45826
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating excitement or fun experiences

    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
    608
    +0.11
    0.5%
    620
    +0.10
    0.4%
    2
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.11
    0.04
    608
    +0.10
    0.03
    665
    +0.10
    0.03
    Negative Logits
     objectionable
    -0.78
    calling
    -0.74
    soDeliveryDate
    -0.71
    rising
    -0.71
    ivist
    -0.69
     flagged
    -0.69
    matter
    -0.64
    Recommended
    -0.63
    é¾įå¥ij士
    -0.62
     accounts
    -0.61
    POSITIVE LOGITS
     behold
    1.03
     learn
    0.94
     see
    0.91
    ggles
    0.91
     hear
    0.91
     collaborate
    0.90
     revisit
    0.89
     assemble
    0.88
     recreate
    0.87
     emulate
    0.87
    Activations Density 0.059%

    No Known Activations