© 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. 22468
    Prev
    Next
    INDEX
    Explanations

    references to the events and dates surrounding the September 11, 2001 attacks

    oai_token-act-pair · gpt-4o-miniTriggered 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
    759
    +0.11
    0.5%
    51
    +0.09
    0.4%
    98
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.11
    0.03
    306
    +0.09
    0.03
    98
    +0.09
    0.03
    Negative Logits
     scoop
    -0.72
    ãĤ¨ãĥ«
    -0.67
    igham
    -0.65
    abase
    -0.62
     Annex
    -0.61
     Gaul
    -0.59
     Folder
    -0.59
     Jinn
    -0.58
    =/
    -0.57
     cog
    -0.57
    POSITIVE LOGITS
    roth
    0.80
    interstitial
    0.77
    Downloadha
    0.73
    owship
    0.67
    aquin
    0.65
    ools
    0.64
     holidays
    0.63
    warts
    0.63
    akespeare
    0.62
    adish
    0.62
    Activations Density 0.071%

    No Known Activations