© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9138
    Prev
    Next
    INDEX
    Explanations

    sequences of phrases where a sentence starts or ends

    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
    480
    +0.41
    2.0%
    266
    +0.12
    0.6%
    373
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.41
    0.01
    6
    +0.12
    0.07
    720
    +0.09
    0.06
    Negative Logits
     spons
    -0.77
    icient
    -0.72
     specialty
    -0.69
     finer
    -0.67
    eware
    -0.66
     hobby
    -0.66
     preference
    -0.65
    iciency
    -0.64
     defic
    -0.64
     suitable
    -0.64
    POSITIVE LOGITS
     Disapp
    0.84
     tragedy
    0.79
    Was
    0.78
     pandemonium
    0.75
     Hiroshima
    0.74
     fateful
    0.73
     Watergate
    0.73
     tragedies
    0.71
     happened
    0.70
     woke
    0.69
    Activations Density 0.751%

    No Known Activations