© 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 49152
    9. 8-RES_FS49152-JB
    11. 45640
    Prev
    Next
    INDEX
    Explanations

    expressions of strong opinions or emotions regarding social issues

    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
    640
    +0.28
    1.3%
    372
    +0.09
    0.4%
    328
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.28
    0.04
    328
    +0.09
    0.02
    372
    +0.08
    0.02
    Negative Logits
     Cent
    -0.69
     ageing
    -0.66
    chnology
    -0.63
     hiber
    -0.62
     regeneration
    -0.61
     endeavour
    -0.61
     Franç
    -0.61
     Quart
    -0.61
    zed
    -0.60
    apon
    -0.60
    POSITIVE LOGITS
    Fans
    0.91
    Looks
    0.89
    BRE
    0.87
    Actor
    0.84
    Rail
    0.82
    Speaking
    0.82
    Sorry
    0.81
    Liter
    0.81
    Yep
    0.81
    Fuck
    0.81
    Activations Density 0.070%

    No Known Activations