© 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. 12-RES-JB
    11. 4859
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geological features, especially rocks and minerals

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to geological features, specifically various types of rocks

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ilities
    -0.68
     Nationwide
    -0.64
    iator
    -0.64
     Legislative
    -0.64
    ãĥ¥
    -0.64
     Hust
    -0.63
     Dragonbound
    -0.63
     Priebus
    -0.62
    iating
    -0.62
     Coulter
    -0.61
    POSITIVE LOGITS
     formations
    1.13
     quar
    1.08
     quarry
    1.07
    falls
    1.05
    fall
    0.93
     formation
    0.89
     cliffs
    0.88
    crete
    0.86
     ledge
    0.85
     slab
    0.85
    Activations Density 0.051%

    No Known Activations