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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18864
    Prev
    Next
    INDEX
    Explanations

    locations or places mentioned in an article as being supported or featured

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    27
    +0.11
    0.5%
    274
    +0.10
    0.5%
    247
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.11
    0.02
    27
    +0.10
    0.02
    274
    +0.10
    0.02
    Negative Logits
    ccording
    -0.69
    roots
    -0.65
    agall
    -0.64
    ISM
    -0.61
    olid
    -0.60
    relative
    -0.59
     coinc
    -0.57
     Orig
    -0.57
    diagn
    -0.56
    ISH
    -0.56
    POSITIVE LOGITS
     below
    1.01
    below
    0.88
     section
    0.87
     comments
    0.81
     forums
    0.75
     Below
    0.75
     sections
    0.75
     sidebar
    0.74
     BELOW
    0.74
    ebin
    0.72
    Activations Density 0.028%

    No Known Activations