© 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. 22870
    Prev
    Next
    INDEX
    Explanations

    concepts related to the social dynamics of altruism and self-interest

    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
    393
    +0.20
    0.9%
    526
    +0.12
    0.6%
    167
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.20
    0.14
    393
    +0.12
    0.11
    608
    +0.11
    0.11
    Negative Logits
    zai
    -0.68
    illon
    -0.68
    >>>>>>>>
    -0.67
    zon
    -0.67
     sprang
    -0.65
    waukee
    -0.64
    Turkey
    -0.63
    ACP
    -0.63
    soDeliveryDate
    -0.62
    amar
    -0.62
    POSITIVE LOGITS
     slightest
    1.48
     same
    1.29
     smallest
    1.21
     highest
    1.16
     wearer
    1.16
     entirety
    1.12
     weakest
    1.12
     simplest
    1.09
     proverbial
    1.08
     opposite
    1.08
    Activations Density 0.606%

    No Known Activations