© 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. 12623
    Prev
    Next
    INDEX
    Explanations

    player names with unique characters or accents

    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
    373
    +0.16
    0.8%
    655
    +0.12
    0.6%
    470
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.16
    -0.01
    232
    +0.12
    0.04
    659
    +0.11
    0.03
    Negative Logits
     Canterbury
    -0.58
    ufact
    -0.57
     relief
    -0.53
     duties
    -0.53
     extinction
    -0.52
    ħĭ
    -0.52
    pta
    -0.52
     Ashes
    -0.52
     generic
    -0.51
    caps
    -0.51
    POSITIVE LOGITS
    д
    0.75
    rek
    0.72
    gyn
    0.68
     Mehran
    0.68
    wald
    0.66
    osh
    0.65
    ü
    0.64
    afi
    0.63
    CHA
    0.63
    и
    0.62
    Activations Density 0.098%

    No Known Activations