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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22989
    Prev
    Next
    INDEX
    Explanations

    concepts related to plans, actions, and significant outcomes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    679
    +0.10
    0.5%
    352
    +0.09
    0.4%
    109
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.10
    0.06
    341
    +0.09
    0.04
    255
    +0.09
    0.04
    Negative Logits
    ZI
    -0.64
    Tes
    -0.59
     Lonely
    -0.56
    dden
    -0.55
     Tablet
    -0.55
     mockery
    -0.55
    Redd
    -0.55
     ty
    -0.54
    Lens
    -0.53
     Wr
    -0.53
    POSITIVE LOGITS
     consisted
    0.99
     includes
    0.90
     include
    0.87
     expired
    0.85
     culminated
    0.82
     resulted
    0.81
     included
    0.80
     came
    0.76
     stemmed
    0.76
     consists
    0.75
    Activations Density 0.305%

    No Known Activations