© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 13197
    Prev
    Next
    INDEX
    Explanations

    terms related to personal beliefs, societal issues, and empowerment

    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
    +0.19
    1.0%
    756
    +0.17
    0.8%
    762
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.19
    -0.01
    762
    +0.17
    0.09
    665
    +0.10
    0.08
    Negative Logits
     Spoiler
    -0.64
     Precision
    -0.62
     Tarant
    -0.62
     Gould
    -0.59
     marquee
    -0.58
     Pumpkin
    -0.57
     Canaver
    -0.57
     Cannes
    -0.55
     Ange
    -0.55
     Horizon
    -0.54
    POSITIVE LOGITS
     themselves
    1.37
     selves
    1.09
    selves
    1.06
     voluntarily
    0.94
     willingly
    0.94
     behave
    0.93
     individually
    0.82
     migrate
    0.81
     resent
    0.80
     their
    0.80
    Activations Density 0.798%

    No Known Activations