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. 23415
    Prev
    Next
    INDEX
    Explanations

    forms of the word "end" and its variations, usually related to completion or conclusion

    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
    373
    +0.10
    0.5%
    591
    +0.10
    0.5%
    356
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.01
    701
    +0.10
    0.04
    284
    +0.09
    0.03
    Negative Logits
     Rabbit
    -0.83
     Rac
    -0.66
     Chau
    -0.65
     Valkyrie
    -0.64
     Lack
    -0.64
     Beautiful
    -0.64
     Rack
    -0.63
     Bron
    -0.62
     Spo
    -0.60
    CLA
    -0.60
    POSITIVE LOGITS
    ences
    0.92
    ciating
    0.92
    agues
    0.91
    anship
    0.90
    aults
    0.90
    acters
    0.88
    ciation
    0.87
    ettings
    0.86
    ents
    0.85
    ational
    0.85
    Activations Density 0.122%

    No Known Activations