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

    Neuronpedia

    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 12288
    9. 8-RES_FS12288-JB
    11. 1842
    Prev
    Next
    INDEX
    Explanations

    adverbs modifying the certainty of statements

    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
    377
    +0.10
    0.5%
    378
    +0.10
    0.4%
    447
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    45
    +0.10
    0.02
    8
    +0.10
    0.03
    733
    +0.09
    0.02
    Negative Logits
    rella
    -0.84
    aily
    -0.82
    eport
    -0.81
    enaries
    -0.74
    enary
    -0.72
    uese
    -0.71
    ntil
    -0.71
    animous
    -0.70
    lé
    -0.67
    etime
    -0.66
    POSITIVE LOGITS
     deline
    1.03
     identifiable
    0.93
     distinguish
    0.89
     differentiated
    0.87
     marked
    0.83
     differentiate
    0.80
     effected
    0.79
     outnumbered
    0.78
     communicated
    0.76
     labelled
    0.76
    Activations Density 0.063%

    No Known Activations