© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 25998
    Prev
    Next
    INDEX
    Explanations

    quantitative statistics and metrics related to online engagement and health care systems

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    Neuron Alignment
    Index
    Value
    % of L₁
    459
    +0.15
    0.7%
    756
    +0.12
    0.5%
    544
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.15
    0.08
    575
    +0.12
    0.07
    459
    +0.11
    0.06
    Negative Logits
    ©¶æ
    -0.74
     ts
    -0.58
     Ts
    -0.53
    yss
    -0.53
    gor
    -0.53
    addons
    -0.51
    wered
    -0.49
     Hung
    -0.49
    ahon
    -0.48
     Deaths
    -0.47
    POSITIVE LOGITS
     accordingly
    1.13
     thereafter
    1.12
    .[
    1.06
    .(
    0.99
    .<
    0.99
    +.
    0.98
    .
    0.97
    *.
    0.90
    .*
    0.86
    ."[
    0.85
    Activations Density 0.635%

    No Known Activations