© 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 49152
    9. 8-RES_FS49152-JB
    11. 45731
    Prev
    Next
    INDEX
    Explanations

    references to significant public figures and their actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.15
    0.7%
    373
    +0.11
    0.5%
    244
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.15
    0.09
    352
    +0.11
    0.09
    103
    +0.09
    0.08
    Negative Logits
     shack
    -0.70
     Belg
    -0.68
     Ambro
    -0.67
     Guinness
    -0.67
     polyg
    -0.66
     tremend
    -0.65
     sew
    -0.65
     Unic
    -0.64
     postal
    -0.64
     Shap
    -0.63
    POSITIVE LOGITS
    ¬
    1.03
    ħ
    1.01
    ĺ
    0.97
    ¡
    0.96
    ı
    0.96
    ¹
    0.95
    Ń
    0.95
    Ļ
    0.94
    ¤
    0.94
    Ķ
    0.93
    Activations Density 0.124%

    No Known Activations