© 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. 18765
    Prev
    Next
    INDEX
    Explanations

    names of political figures

    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
    631
    +0.11
    0.5%
    616
    +0.09
    0.4%
    545
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.03
    406
    +0.09
    0.03
    659
    +0.09
    0.03
    Negative Logits
    pter
    -0.87
    ources
    -0.70
    hend
    -0.70
    ship
    -0.69
    ships
    -0.69
    lance
    -0.68
    inus
    -0.66
    oslav
    -0.65
    effic
    -0.64
    occ
    -0.64
    POSITIVE LOGITS
    adesh
    0.61
     è£ıè
    0.61
     lett
    0.60
     Point
    0.55
     corpus
    0.54
     Literature
    0.54
     warr
    0.53
     punch
    0.53
    she
    0.52
     surv
    0.51
    Activations Density 0.104%

    No Known Activations