© 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. 1862
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenging authority or advocating for victims of various types of crimes and injustices

    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
    87
    +0.13
    0.6%
    459
    +0.12
    0.5%
    491
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.13
    0.11
    440
    +0.12
    0.08
    430
    +0.09
    0.09
    Negative Logits
     pact
    -0.70
     groundwork
    -0.66
     covenant
    -0.65
     roadmap
    -0.65
     affili
    -0.63
     fullest
    -0.62
     consolidation
    -0.62
     compact
    -0.62
    ":"/
    -0.61
     bookmark
    -0.60
    POSITIVE LOGITS
     Afterwards
    0.92
     Worse
    0.92
     Needless
    0.91
     Apparently
    0.87
     Later
    0.87
     Guess
    0.86
     Luckily
    0.84
     Curious
    0.83
     Similarly
    0.83
     Suddenly
    0.81
    Activations Density 0.707%

    No Known Activations