© 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. 7443
    Prev
    Next
    INDEX
    Explanations

    opinions and statements emphasizing abundance

    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
    596
    +0.11
    0.5%
    216
    +0.11
    0.5%
    195
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    596
    +0.11
    0.02
    760
    +0.11
    0.02
    376
    +0.10
    0.01
    Negative Logits
    ensis
    -0.70
    anwhile
    -0.69
    anium
    -0.67
    ordan
    -0.65
    estamp
    -0.65
    acia
    -0.63
    Moh
    -0.62
    abad
    -0.62
    into
    -0.62
    sole
    -0.61
    POSITIVE LOGITS
     of
    0.79
     thereof
    0.77
     else
    0.74
     deserving
    0.72
    entimes
    0.71
     enough
    0.67
    poons
    0.66
    hots
    0.65
     tasty
    0.64
     ample
    0.64
    Activations Density 0.021%

    No Known Activations