© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 328
    Prev
    Next
    INDEX
    Explanations

    dates represented in a specific format

    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
    512
    +0.11
    0.5%
    373
    +0.11
    0.5%
    627
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    627
    +0.11
    0.03
    124
    +0.11
    0.04
    512
    +0.10
    0.03
    Negative Logits
    uyomi
    -0.63
     Tile
    -0.62
     uncovered
    -0.61
     americ
    -0.61
     Penn
    -0.60
     (),
    -0.58
     Stand
    -0.57
     tox
    -0.57
     BMC
    -0.56
     child
    -0.56
    POSITIVE LOGITS
    3
    1.08
    4
    1.06
    6
    1.04
    5
    1.03
    7
    1.01
    2
    0.99
    8
    0.98
    10
    0.98
    14
    0.98
    13
    0.97
    Activations Density 0.115%

    No Known Activations