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. 1090
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical locations or settings

    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
    737
    +0.11
    0.5%
    551
    +0.10
    0.4%
    167
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.11
    0.02
    500
    +0.10
    0.02
    551
    +0.10
    0.01
    Negative Logits
    ufact
    -0.86
    issance
    -0.79
    egal
    -0.79
    orthy
    -0.77
    atoon
    -0.77
    ignty
    -0.75
    emon
    -0.73
    hur
    -0.70
    inen
    -0.69
    wow
    -0.69
    POSITIVE LOGITS
    stones
    1.19
    bars
    0.92
    busters
    0.88
    nered
    0.80
    naire
    0.78
     corner
    0.78
    istas
    0.78
    chester
    0.76
     corners
    0.75
    ing
    0.75
    Activations Density 0.016%

    No Known Activations