© 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 24576
    5. 8-RES_FS24576-JB
    6. 9253
    Prev
    Next
    INDEX
    Explanations

    details related to features and customization options of a product, possibly a 3D printer

    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
    661
    +0.11
    0.5%
    314
    +0.11
    0.5%
    331
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    0.01
    659
    +0.11
    0.05
    176
    +0.09
    0.04
    Negative Logits
     Miko
    -0.70
     Herz
    -0.70
     Afric
    -0.69
     Hayden
    -0.69
     Libertarian
    -0.69
     Esper
    -0.68
     Saban
    -0.68
     Wass
    -0.66
     Abu
    -0.66
     tha
    -0.65
    POSITIVE LOGITS
    ailability
    1.11
    erate
    1.09
    ipment
    1.05
    ufficient
    1.04
    autions
    1.04
    itting
    1.03
    requency
    1.01
    aintain
    1.01
    seless
    1.00
    ature
    1.00
    Activations Density 0.226%

    No Known Activations