© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 41635
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and technology concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    314
    +0.15
    0.7%
    362
    +0.12
    0.6%
    723
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    738
    +0.15
    0.02
    78
    +0.12
    0.02
    363
    +0.10
    0.03
    Negative Logits
     helicop
    -0.86
     symb
    -0.62
    sbm
    -0.62
    âĶĢâĶĢâĶĢâĶĢ
    -0.62
    ocrin
    -0.61
    cour
    -0.61
     contrace
    -0.61
    meet
    -0.59
     pse
    -0.57
     ........
    -0.57
    POSITIVE LOGITS
     hers
    0.63
    amia
    0.57
    ection
    0.57
    igmat
    0.56
     TAMADRA
    0.56
    rypt
    0.56
     Isles
    0.56
    isSpecialOrderable
    0.56
    realDonaldTrump
    0.55
     Bulg
    0.55
    Activations Density 0.201%

    No Known Activations