© 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. 15911
    Prev
    Next
    INDEX
    Explanations

    descriptions or discussions related to specific products or objects

    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
    447
    +0.12
    0.6%
    461
    +0.12
    0.5%
    420
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.12
    0.07
    563
    +0.12
    0.07
    452
    +0.12
    0.06
    Negative Logits
    ãĥķãĤ¡
    -0.75
    airy
    -0.62
    farious
    -0.61
     dstg
    -0.60
    Hey
    -0.60
     heavens
    -0.59
    ãĤ¤ãĥĪ
    -0.59
    frac
    -0.58
    Ĭ±
    -0.57
    riad
    -0.56
    POSITIVE LOGITS
     also
    1.32
     furthermore
    1.24
     additionally
    1.20
     therefore
    1.13
     moreover
    1.11
     emphasizes
    1.00
     however
    0.97
     consists
    0.96
     utilizes
    0.93
     retains
    0.92
    Activations Density 0.464%

    No Known Activations