© 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 EvalsExportsinterp-engineNEWAPI 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. 13773
    Prev
    Next
    INDEX
    Explanations

    terms related to complex social, political, and historical contexts

    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
    653
    +0.10
    0.5%
    94
    +0.09
    0.4%
    623
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    428
    +0.10
    0.04
    151
    +0.09
    0.05
    429
    +0.09
    0.03
    Negative Logits
    ynthesis
    -0.72
    iper
    -0.69
    rology
    -0.65
    aterial
    -0.64
    different
    -0.64
    rolog
    -0.63
     Blasio
    -0.62
    roller
    -0.62
    rio
    -0.62
    Die
    -0.59
    POSITIVE LOGITS
     enough
    1.23
    nesses
    1.00
     ones
    0.91
    ly
    0.90
    ially
    0.86
    aneously
    0.83
    izes
    0.81
     amounts
    0.81
     additions
    0.79
    iates
    0.79
    Activations Density 0.302%

    No Known Activations