© 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 EvalsExportsAPI 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. 11029
    Prev
    Next
    INDEX
    Explanations

    Canadian-related terms, especially those related to legal or political 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
    579
    +0.12
    0.5%
    309
    +0.12
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.01
    284
    +0.12
    0.01
    579
    +0.11
    0.01
    Negative Logits
    bush
    -0.80
     regress
    -0.67
     sterling
    -0.67
     Cheong
    -0.60
     Ruk
    -0.57
     Cantor
    -0.57
     fronts
    -0.56
     counter
    -0.55
     Emanuel
    -0.55
     quarters
    -0.55
    POSITIVE LOGITS
    adian
    0.79
    ue
    0.78
    cially
    0.77
    illo
    0.74
    aukee
    0.74
    cial
    0.73
    ildo
    0.73
    rouse
    0.71
    obos
    0.71
    igue
    0.70
    Activations Density 0.048%

    No Known Activations