© 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. 837
    Prev
    Next
    INDEX
    Explanations

    references to events or reports from a war-torn location

    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
    480
    +0.48
    2.5%
    464
    +0.11
    0.6%
    127
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.48
    0.01
    266
    +0.11
    0.14
    362
    +0.09
    0.11
    Negative Logits
    ecause
    -0.71
     insofar
    -0.66
     anecd
    -0.62
     caveats
    -0.57
    arij
    -0.55
     concedes
    -0.54
    iple
    -0.54
    ngth
    -0.53
    inen
    -0.52
     consulted
    -0.52
    POSITIVE LOGITS
    )))
    0.61
     eternity
    0.57
     respectively
    0.56
    ))))
    0.55
    Merit
    0.54
     Frie
    0.54
    '.
    0.54
     eco
    0.53
     Sochi
    0.52
     )))
    0.51
    Activations Density 2.885%

    No Known Activations