© 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. 2530
    Prev
    Next
    INDEX
    Explanations

    phrases related to political statements or criticisms

    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
    36
    +0.16
    0.8%
    102
    +0.15
    0.7%
    314
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.16
    0.04
    316
    +0.15
    0.03
    704
    +0.13
    0.02
    Negative Logits
     Blacks
    -0.80
     lobb
    -0.80
     administrators
    -0.80
     Izan
    -0.78
     addresses
    -0.78
     viewers
    -0.77
     Asians
    -0.77
     blockers
    -0.77
     ups
    -0.75
     exits
    -0.75
    POSITIVE LOGITS
    very
    1.36
    classic
    1.24
    highly
    1.23
    reasonable
    1.22
    complete
    1.22
    few
    1.21
    significant
    1.21
    little
    1.21
    huge
    1.16
    typ
    1.14
    Activations Density 0.036%

    No Known Activations