© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 16930
    Prev
    Next
    INDEX
    Explanations

    instances of the word "king" with varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "king."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ric
    -0.73
    è¯
    -0.70
     redistributed
    -0.66
    anches
    -0.66
    ucci
    -0.62
    ãĥ¼ãĥ³
    -0.62
    IJ
    -0.62
     helicop
    -0.61
    ENC
    -0.59
     compe
    -0.59
    POSITIVE LOGITS
    doms
    1.12
    king
    1.09
    hiro
    0.92
    lift
    0.92
    dom
    0.88
    ham
    0.87
    apeake
    0.86
    lass
    0.86
    leon
    0.84
    hammer
    0.84
    Activations Density 0.009%

    No Known Activations