© 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. 8-RES-JB
    11. 13036
    Prev
    Next
    INDEX
    Explanations

    names or terms related to famous individuals or personalities, especially with the word part "Di" present

    oai_token-act-pair · gpt-3.5-turbo

    words related to the name "Diab" and its various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     envy
    -0.74
     responsiveness
    -0.73
     hire
    -0.63
    ãĤ´ãĥ³
    -0.63
    nington
    -0.59
     pads
    -0.58
     corrosion
    -0.57
     reins
    -0.56
     rentals
    -0.56
     ILCS
    -0.56
    POSITIVE LOGITS
    pora
    1.03
    nih
    0.94
    asio
    0.93
    liction
    0.81
    andowski
    0.79
    ij士
    0.79
    arb
    0.78
    ache
    0.74
    cious
    0.74
    ocrine
    0.74
    Activations Density 0.068%

    No Known Activations