© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 37582
    Prev
    Next
    INDEX
    Explanations

    political and social commentary on controversial 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
    87
    +0.18
    0.9%
    330
    +0.10
    0.5%
    645
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.18
    -0.01
    283
    +0.10
    0.02
    712
    +0.09
    0.02
    Negative Logits
    iple
    -0.70
     partName
    -0.68
    MAS
    -0.63
     Monthly
    -0.60
    lease
    -0.58
     Pinball
    -0.57
    ibble
    -0.57
     Illust
    -0.56
     Lists
    -0.56
     Announce
    -0.56
    POSITIVE LOGITS
     "'
    1.01
     "[
    0.90
     "â̦
    0.87
     "
    0.87
     "...
    0.82
     rapists
    0.75
     terrorists
    0.72
     unfairly
    0.70
     ".
    0.70
     "(
    0.67
    Activations Density 0.638%

    No Known Activations