© 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. 11-RES-JB
    11. 12743
    Prev
    Next
    INDEX
    Explanations

    proper nouns, possibly names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    headlines or elements related to news articles or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entimes
    -0.65
     someday
    -0.65
     perenn
    -0.60
     endeavor
    -0.59
     structured
    -0.55
     denomin
    -0.55
     itch
    -0.55
     liv
    -0.54
     aptly
    -0.54
     always
    -0.54
    POSITIVE LOGITS
    Saudi
    1.03
    Israeli
    0.97
     Yemeni
    0.97
    Pakistan
    0.97
     Saudi
    0.95
    Iran
    0.95
     Malaysian
    0.94
     Rohingya
    0.93
    Syrian
    0.92
     Pakistani
    0.92
    Activations Density 0.535%

    No Known Activations