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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 1925
    Prev
    Next
    INDEX
    Explanations

    text related to e-books and other electronic resources

    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
    57
    +0.11
    0.5%
    314
    +0.11
    0.5%
    631
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.11
    0.03
    631
    +0.11
    0.03
    384
    +0.11
    0.03
    Negative Logits
     Anthem
    -0.71
     Kitchen
    -0.70
     NEC
    -0.67
     Kats
    -0.63
     Katz
    -0.60
    ãĤ¤ãĥĪ
    -0.60
     Ernst
    -0.60
     Burton
    -0.59
     Vulkan
    -0.59
     Fernand
    -0.59
    POSITIVE LOGITS
    tymology
    1.40
    gypt
    1.27
    ternally
    1.23
    ighth
    1.22
    agles
    1.22
    arthed
    1.19
    ugen
    1.13
    thereum
    1.12
    lements
    1.06
    pee
    1.06
    Activations Density 0.036%

    No Known Activations