© 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 24576
    9. 8-RES_FS24576-JB
    11. 9279
    Prev
    Next
    INDEX
    Explanations

    references to specific events or concepts from various texts

    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
    686
    +0.10
    0.5%
    141
    +0.10
    0.5%
    236
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.10
    0.04
    510
    +0.10
    0.05
    575
    +0.09
    0.06
    Negative Logits
    Natural
    -0.63
     Weston
    -0.58
     Holden
    -0.54
    ertility
    -0.54
    ustomed
    -0.54
    umar
    -0.54
     ACTIONS
    -0.53
    Nap
    -0.52
     ));
    -0.51
    lees
    -0.51
    POSITIVE LOGITS
    [/
    1.54
    »
    1.45
    ãĢij
    1.40
    ]"
    1.38
    ãĢı
    1.36
    ãĢį
    1.36
    \)
    1.35
    "—
    1.31
    "-
    1.30
    %"
    1.27
    Activations Density 0.887%

    No Known Activations