© 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 1536
    9. 8-RES_FS1536-JB
    11. 1139
    Prev
    Next
    INDEX
    Explanations

    prompts for feedback or opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    726
    +0.11
    0.5%
    380
    +0.10
    0.5%
    313
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.11
    0.10
    424
    +0.10
    0.07
    184
    +0.09
    0.05
    Negative Logits
    inational
    -0.62
     Emanuel
    -0.61
     marketed
    -0.61
     blamed
    -0.61
     equilibrium
    -0.60
    cemic
    -0.60
    Ö¼
    -0.60
    ¥µ
    -0.60
     ubiqu
    -0.59
    Said
    -0.59
    POSITIVE LOGITS
     Submit
    1.06
     :)
    1.03
     bookmark
    1.00
     ;)
    0.99
     feedback
    0.99
     Feedback
    0.98
     submissions
    0.98
     suggestions
    0.96
     ðŁĻĤ
    0.94
     please
    0.93
    Activations Density 3.835%

    No Known Activations