© 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. 6249
    Prev
    Next
    INDEX
    Explanations

    words related to communication and exchanging information through speech

    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
    679
    +0.11
    0.5%
    283
    +0.10
    0.5%
    720
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.11
    0.04
    184
    +0.10
    0.03
    248
    +0.09
    0.03
    Negative Logits
     sidx
    -0.86
    adesh
    -0.84
    elsh
    -0.73
    imposed
    -0.70
    conservancy
    -0.70
    berus
    -0.69
    tis
    -0.68
    ibaba
    -0.67
    idges
    -0.67
    ateral
    -0.67
    POSITIVE LOGITS
    tale
    1.19
     us
    1.07
     him
    1.06
     me
    1.04
     them
    0.96
    ingly
    0.88
     stories
    0.84
     reporters
    0.82
     jokes
    0.81
     tales
    0.77
    Activations Density 0.057%

    No Known Activations