© 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. 19365
    Prev
    Next
    INDEX
    Explanations

    details related to finances, politics, and military operations

    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
    35
    +0.10
    0.5%
    257
    +0.10
    0.5%
    236
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.10
    0.06
    258
    +0.10
    0.06
    90
    +0.10
    0.05
    Negative Logits
    ãĥį
    -0.71
     confir
    -0.66
    Orig
    -0.64
    é¾įå
    -0.61
     Klu
    -0.58
    ãĥ«
    -0.58
    ãĤ¨ãĥ«
    -0.57
     Pengu
    -0.56
    Ô
    -0.55
    APP
    -0.54
    POSITIVE LOGITS
     etc
    1.40
    etc
    1.00
     ect
    0.94
    âĢ¦)
    0.88
    ,...
    0.88
    ,
    0.86
    âĢ¦
    0.80
    ...)
    0.76
     âĢ¦
    0.74
     blah
    0.70
    Activations Density 0.243%

    No Known Activations