© 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. 9316
    Prev
    Next
    INDEX
    Explanations

    phrases related to teamwork, political support, and political conflicts

    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
    82
    +0.11
    0.5%
    414
    +0.10
    0.5%
    463
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    758
    +0.11
    0.03
    526
    +0.10
    0.01
    82
    +0.10
    0.03
    Negative Logits
    NESS
    -0.73
    ossier
    -0.67
    enery
    -0.58
    iage
    -0.56
    CRIP
    -0.56
    ration
    -0.55
    Council
    -0.55
    gar
    -0.55
    etsk
    -0.54
    rica
    -0.54
    POSITIVE LOGITS
    lessly
    1.20
    ishly
    1.16
    arily
    1.07
    ously
    1.06
    edly
    1.03
    wise
    1.00
    aneously
    0.96
    ically
    0.96
    ally
    0.96
    ologically
    0.93
    Activations Density 0.171%

    No Known Activations