© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 10157
    Prev
    Next
    INDEX
    Explanations

    content related to news articles, updates from sources like "Business Insider" and "Woman's Day," and events like charity bowling nights

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    373
    +0.18
    0.8%
    685
    +0.11
    0.5%
    233
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    233
    +0.18
    0.03
    373
    +0.11
    -0.02
    755
    +0.10
    0.02
    Negative Logits
    ij士
    -0.80
     majority
    -0.60
    oster
    -0.58
    ãĤ´ãĥ³
    -0.56
     Skydragon
    -0.56
     Peaks
    -0.54
    asma
    -0.54
     Kers
    -0.53
    @@@@
    -0.53
    ãĥı
    -0.52
    POSITIVE LOGITS
    erous
    0.89
     than
    0.87
    than
    0.82
    facebook
    0.77
    efficient
    0.69
    usat
    0.66
    edly
    0.64
     Videos
    0.63
    culated
    0.63
    itional
    0.61
    Activations Density 0.178%

    No Known Activations