© 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. 10207
    Prev
    Next
    INDEX
    Explanations

    information related to updates, releases, and events in various media and fields

    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
    447
    +0.61
    4.3%
    481
    +0.37
    2.6%
    138
    +0.14
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.61
    0.07
    639
    +0.37
    0.10
    674
    +0.14
    0.08
    Negative Logits
     theirs
    -0.53
     circulation
    -0.49
     embargo
    -0.48
     amnesty
    -0.48
     reper
    -0.47
     tradem
    -0.47
     abandon
    -0.46
     obligation
    -0.46
     rushes
    -0.46
     displacement
    -0.46
    POSITIVE LOGITS
    Untitled
    1.03
    Abstract
    0.98
    Description
    0.98
    WASHINGTON
    0.98
    CLOSE
    0.94
    CTV
    0.92
    Overview
    0.90
    SAN
    0.88
    Welcome
    0.87
    Still
    0.84
    Activations Density 0.087%

    No Known Activations