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. 43204
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or important subjects in a discussion

    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
    +0.24
    1.2%
    447
    +0.22
    1.1%
    393
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.24
    0.10
    385
    +0.22
    0.10
    608
    +0.17
    0.10
    Negative Logits
     âĢº
    -0.78
    --+
    -0.76
    thood
    -0.75
    etooth
    -0.72
    contained
    -0.68
    ustom
    -0.67
    LOD
    -0.66
    .","
    -0.65
    bg
    -0.65
    pection
    -0.65
    POSITIVE LOGITS
    resa
    1.20
     irony
    1.17
     implication
    1.12
    oret
    1.10
     truth
    1.09
     slightest
    1.08
     facts
    1.04
     hypocrisy
    1.02
     Economist
    1.02
     fact
    1.01
    Activations Density 0.404%

    No Known Activations