© 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. 16396
    Prev
    Next
    INDEX
    Explanations

    names of individuals, likely related to news or events

    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
    745
    +0.12
    0.5%
    737
    +0.11
    0.5%
    337
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.04
    406
    +0.11
    0.04
    659
    +0.10
    0.04
    Negative Logits
    ©¶æ
    -0.72
    _-
    -0.67
    achev
    -0.65
     Aval
    -0.64
    ãĤ¨
    -0.63
    ãĤ¶
    -0.61
    Ĥ¬
    -0.61
     artificially
    -0.61
    Ħ¢
    -0.60
    itol
    -0.60
    POSITIVE LOGITS
    merce
    0.92
    aii
    0.80
    ipeg
    0.79
    schild
    0.76
    ows
    0.71
    ibaba
    0.71
    gan
    0.69
    wo
    0.68
    bee
    0.68
    arta
    0.67
    Activations Density 0.146%

    No Known Activations