© 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. 24295
    Prev
    Next
    INDEX
    Explanations

    terms related to violence and safety issues involving women and police interactions

    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
    447
    +0.20
    0.9%
    481
    +0.16
    0.8%
    493
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.20
    0.07
    146
    +0.16
    0.06
    481
    +0.10
    0.06
    Negative Logits
    lopp
    -0.78
     ILCS
    -0.71
    ega
    -0.70
    Narr
    -0.69
    iencies
    -0.67
    join
    -0.66
    catentry
    -0.64
    rozen
    -0.64
    Split
    -0.64
    agall
    -0.63
    POSITIVE LOGITS
     perpetrated
    0.95
     retaliation
    0.87
     unjust
    0.86
     arising
    0.79
     stemming
    0.75
     senseless
    0.75
     unprepared
    0.75
     indiscrim
    0.73
     retali
    0.72
     unfairly
    0.72
    Activations Density 0.329%

    No Known Activations