© 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. 7785
    Prev
    Next
    INDEX
    Explanations

    people or places named "Nam" in the text

    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
    187
    +0.15
    0.7%
    52
    +0.12
    0.5%
    739
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.01
    187
    +0.12
    0.01
    232
    +0.11
    0.01
    Negative Logits
     posit
    -0.70
     almonds
    -0.66
     yeast
    -0.65
     preferential
    -0.63
     cider
    -0.62
     espresso
    -0.62
     ants
    -0.61
     briefs
    -0.60
     inhib
    -0.60
     resultant
    -0.59
    POSITIVE LOGITS
    eless
    1.23
    ibia
    1.14
    aji
    1.09
    azing
    1.01
    ulus
    0.97
    pered
    0.95
    achu
    0.94
    aran
    0.92
    emon
    0.92
    ankind
    0.92
    Activations Density 0.018%

    No Known Activations