© 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. 4403
    Prev
    Next
    INDEX
    Explanations

    clothing-related incidents or disputes

    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
    481
    +0.17
    0.8%
    373
    +0.14
    0.6%
    420
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    627
    +0.17
    0.03
    470
    +0.14
    0.03
    420
    +0.13
    0.05
    Negative Logits
    defense
    -0.96
     Organizations
    -0.91
     organizational
    -0.88
     [&
    -0.86
    Washington
    -0.84
     DOJ
    -0.83
    ospons
    -0.83
     favoring
    -0.79
    Newsletter
    -0.79
     favorably
    -0.78
    POSITIVE LOGITS
     colourful
    1.24
     ITV
    1.19
     humour
    1.14
     apologised
    1.13
     neighbours
    1.12
     £
    1.11
     realise
    1.10
     realised
    1.10
     footballer
    1.10
     paed
    1.08
    Activations Density 1.274%

    No Known Activations