© 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. 11521
    Prev
    Next
    INDEX
    Explanations

    adjectives conveying judgement or value, both positive and negative

    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
    362
    +0.12
    0.6%
    36
    +0.10
    0.5%
    538
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.12
    0.05
    362
    +0.10
    0.03
    538
    +0.10
    0.02
    Negative Logits
    successfully
    -0.90
    2020
    -0.81
    pora
    -0.75
    rity
    -0.73
    egal
    -0.72
    ilitating
    -0.71
    ledged
    -0.70
    later
    -0.70
    lu
    -0.69
     ALSO
    -0.69
    POSITIVE LOGITS
     coincidence
    1.19
     cosmetic
    0.97
     plain
    0.95
     placeholder
    0.90
     curiosity
    0.89
     fig
    0.88
     decoration
    0.85
     reflection
    0.85
     symptom
    0.84
     footnote
    0.82
    Activations Density 0.095%

    No Known Activations