© 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 768
    9. 8-RES_FS768-JB
    11. 730
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership, innovation, and societal progress

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    737
    +0.13
    0.6%
    181
    +0.11
    0.5%
    729
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.13
    0.16
    435
    +0.11
    0.09
    729
    +0.11
    0.12
    Negative Logits
    lav
    -0.95
    weeney
    -0.73
    ãĤ±
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.68
    azel
    -0.67
    byter
    -0.66
     livest
    -0.65
     contracted
    -0.64
    ãĤ¤
    -0.63
    iaries
    -0.62
    POSITIVE LOGITS
    !
    0.82
     ¯
    0.82
    !.
    0.81
     offensively
    0.78
     ;)
    0.75
    .
    0.75
     mentality
    0.74
    !:
    0.73
    !--
    0.72
    !!!
    0.72
    Activations Density 7.184%

    No Known Activations