© 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. 7470
    Prev
    Next
    INDEX
    Explanations

    phrases related to problem-solving, decision-making, and people's strengths and weaknesses

    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
    480
    +0.47
    2.4%
    266
    +0.11
    0.5%
    641
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.47
    0.01
    266
    +0.11
    0.06
    516
    +0.09
    0.04
    Negative Logits
    >>>>>>>>
    -0.73
    pload
    -0.71
     Reloaded
    -0.58
    ////////////////
    -0.57
     Alv
    -0.56
    mobi
    -0.54
     Hast
    -0.52
    ammy
    -0.51
    DragonMagazine
    -0.50
     incorpor
    -0.50
    POSITIVE LOGITS
     otherwise
    0.78
     detriment
    0.68
     pree
    0.68
     deems
    0.68
     already
    0.65
     predetermined
    0.64
     unfavorable
    0.64
    relevant
    0.62
     theirs
    0.62
     themselves
    0.61
    Activations Density 0.440%

    No Known Activations