Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 41631
    Prev
    Next
    INDEX
    Explanations

    phrases or contexts related to rights and regulations

    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
    393
    +0.13
    0.6%
    362
    +0.11
    0.5%
    375
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    611
    +0.13
    0.04
    362
    +0.11
    0.04
    549
    +0.10
    0.03
    Negative Logits
    forge
    -0.69
    â̲
    -0.65
    Catalog
    -0.64
    boxing
    -0.63
    been
    -0.61
    arat
    -0.60
    FBI
    -0.60
    iba
    -0.59
    !'"
    -0.58
    gaming
    -0.58
    POSITIVE LOGITS
     certain
    0.85
     these
    0.80
     oneself
    0.74
     goods
    0.73
    ilts
    0.71
     fluids
    0.69
     those
    0.69
     mankind
    0.66
    minster
    0.66
     various
    0.65
    Activations Density 0.124%

    No Known Activations