© 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. 8024
    Prev
    Next
    INDEX
    Explanations

    emotions and reactions related to disappointment and upset

    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
    720
    +0.10
    0.5%
    659
    +0.10
    0.5%
    380
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.10
    0.05
    445
    +0.10
    0.04
    96
    +0.09
    0.03
    Negative Logits
     Attribution
    -0.82
    imum
    -0.81
     Logo
    -0.78
    vre
    -0.77
    vernment
    -0.76
     Flavoring
    -0.74
    aceutical
    -0.73
    20439
    -0.70
     mosaic
    -0.67
    UA
    -0.66
    POSITIVE LOGITS
     saddened
    1.24
     anxious
    1.16
     frightened
    1.13
     humiliated
    1.13
     nervous
    1.10
     embarrassed
    1.09
     frustrated
    1.09
     disappointed
    1.09
     angry
    1.08
     disgusted
    1.07
    Activations Density 0.300%

    No Known Activations