© 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. 4703
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or social issues

    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
    +0.21
    1.1%
    756
    +0.09
    0.5%
    564
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.21
    0.05
    608
    +0.09
    0.07
    362
    +0.08
    0.06
    Negative Logits
    ':
    -0.58
    !:
    -0.57
    *:
    -0.57
    zai
    -0.57
    ';
    -0.55
    HY
    -0.54
    `.
    -0.53
     although
    -0.53
    ullah
    -0.53
    amiya
    -0.53
    POSITIVE LOGITS
    pires
    0.88
    pired
    0.65
     entails
    0.60
     mattered
    0.59
     constitutes
    0.59
     exceeds
    0.58
     equals
    0.57
     depends
    0.57
    itiz
    0.56
     becomes
    0.55
    Activations Density 0.753%

    No Known Activations