© 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. 45411
    Prev
    Next
    INDEX
    Explanations

    references to religious or ceremonial leadership roles

    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
    695
    +0.09
    0.4%
    232
    +0.09
    0.4%
    137
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.09
    0.01
    289
    +0.09
    0.01
    701
    +0.09
    0.01
    Negative Logits
    âĸ¬âĸ¬
    -0.89
    âĸ¬
    -0.80
    ////////////////////////////////
    -0.66
    sem
    -0.62
    spin
    -0.61
     quo
    -0.60
    ãģ®éŃĶ
    -0.59
     Logged
    -0.59
    HAHA
    -0.58
     fav
    -0.57
    POSITIVE LOGITS
    enty
    1.18
    asma
    1.11
    acement
    1.10
    ength
    1.02
    umbing
    1.02
    acements
    1.02
    ounge
    1.01
    ains
    0.97
    ife
    0.97
    itude
    0.94
    Activations Density 0.009%

    No Known Activations