© 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. 24095
    Prev
    Next
    INDEX
    Explanations

    descriptors related to emotions and experiences, particularly those that evoke strong reactions

    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
    362
    +0.12
    0.5%
    284
    +0.10
    0.4%
    700
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.06
    362
    +0.10
    0.07
    408
    +0.09
    0.07
    Negative Logits
    orthy
    -0.80
    ;;
    -0.76
    arate
    -0.75
    utics
    -0.75
    haps
    -0.75
    OIL
    -0.74
    VERTISEMENT
    -0.73
    yi
    -0.73
    avia
    -0.72
    ADA
    -0.69
    POSITIVE LOGITS
    est
    1.38
    ness
    1.12
    liest
    1.11
     confines
    1.04
     nature
    1.03
     aftermath
    1.00
     notion
    0.93
     underside
    0.91
     aspect
    0.91
     possibility
    0.90
    Activations Density 0.292%

    No Known Activations