© 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 12288
    9. 8-RES_FS12288-JB
    11. 1486
    Prev
    Next
    INDEX
    Explanations

    information related to social issues, such as gender-based violence, refugee treatment, and welfare abuse

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    480
    +0.49
    2.6%
    314
    +0.13
    0.7%
    266
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.49
    0.02
    266
    +0.13
    0.11
    106
    +0.11
    0.07
    Negative Logits
    Operation
    -0.68
     sorcery
    -0.63
     Volcano
    -0.62
     Regulation
    -0.61
     semantics
    -0.59
     Efficiency
    -0.57
     Implementation
    -0.56
     Simple
    -0.56
     inconsistency
    -0.56
     VIDEOS
    -0.55
    POSITIVE LOGITS
     whom
    1.26
    who
    1.01
     who
    0.96
    selves
    0.85
     oppressed
    0.84
     persecuted
    0.81
     victimized
    0.79
     willing
    0.79
    represented
    0.78
     alike
    0.78
    Activations Density 1.693%

    No Known Activations