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. 1221
    Prev
    Next
    INDEX
    Explanations

    media outlets

    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
    496
    +0.12
    0.5%
    455
    +0.11
    0.5%
    114
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.12
    0.02
    455
    +0.11
    0.02
    506
    +0.11
    0.02
    Negative Logits
    potion
    -0.71
    ayne
    -0.70
    lua
    -0.68
    eric
    -0.65
    heed
    -0.64
    nexus
    -0.63
    jri
    -0.62
    ipeg
    -0.62
    skill
    -0.61
    yles
    -0.61
    POSITIVE LOGITS
     outlets
    1.18
     outlet
    1.06
    eval
    0.79
     amplify
    0.76
     Ignore
    0.73
     airing
    0.72
    NPR
    0.70
     ARTICLE
    0.69
     Beir
    0.68
    CNN
    0.68
    Activations Density 0.041%

    No Known Activations