© 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. 15755
    Prev
    Next
    INDEX
    Explanations

    information related to scientific research and studies

    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
    724
    +0.13
    0.6%
    655
    +0.12
    0.6%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.13
    0.06
    724
    +0.12
    0.05
    44
    +0.10
    0.04
    Negative Logits
     derog
    -0.73
    ffen
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.65
    ACTED
    -0.62
     largeDownload
    -0.62
    oris
    -0.60
    ãĤ«
    -0.59
     Dynamics
    -0.59
    NEY
    -0.58
     condem
    -0.58
    POSITIVE LOGITS
    whelming
    0.94
    represent
    0.82
     tripled
    0.81
     1500
    0.80
     dozen
    0.80
    thirds
    0.79
     200
    0.78
     8000
    0.76
    serving
    0.76
    capacity
    0.75
    Activations Density 0.050%

    No Known Activations