© 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. 13051
    Prev
    Next
    INDEX
    Explanations

    the term "nowhere."

    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
    253
    +0.11
    0.5%
    614
    +0.09
    0.4%
    377
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    614
    +0.11
    0.02
    377
    +0.09
    0.02
    422
    +0.09
    0.02
    Negative Logits
     Reef
    -0.80
     mash
    -0.66
    ilt
    -0.65
    tein
    -0.63
    osterone
    -0.62
    uno
    -0.61
    abeth
    -0.60
    seless
    -0.60
    quel
    -0.59
    utenberg
    -0.58
    POSITIVE LOGITS
     else
    1.36
    abouts
    1.07
     Else
    1.01
    Else
    0.99
     Near
    0.89
    near
    0.87
     near
    0.87
    else
    0.77
     nearer
    0.76
    lihood
    0.76
    Activations Density 0.017%

    No Known Activations