© 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 24576
    9. 8-RES_FS24576-JB
    11. 10047
    Prev
    Next
    INDEX
    Explanations

    instances of the word "perfectly" being used to describe a situation or action

    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
    151
    +0.13
    0.6%
    534
    +0.11
    0.5%
    376
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.13
    0.02
    534
    +0.11
    0.02
    565
    +0.09
    0.02
    Negative Logits
    jri
    -0.77
    mere
    -0.77
    anwhile
    -0.76
    ulative
    -0.75
    abies
    -0.71
    gee
    -0.70
    ocene
    -0.70
    NetMessage
    -0.69
    Downloadha
    -0.68
    SEE
    -0.68
    POSITIVE LOGITS
     suited
    1.17
     aligned
    1.06
     timed
    0.99
     positioned
    0.94
     tuned
    0.91
     behaved
    0.89
     encaps
    0.86
     situated
    0.83
     fit
    0.81
     adapted
    0.81
    Activations Density 0.020%

    No Known Activations