© 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. 2303
    Prev
    Next
    INDEX
    Explanations

    mentions of specific places, local businesses, and food items in a city

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

    descriptors of locations and experiences worth visiting or enjoying

    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
     Pastebin
    -0.68
    SPONSORED
    -0.68
     Fixed
    -0.67
     subcontract
    -0.67
     Wikimedia
    -0.66
     redacted
    -0.66
     Cancel
    -0.65
     Oops
    -0.65
     Journalism
    -0.64
    lihood
    -0.63
    POSITIVE LOGITS
     unforgettable
    1.19
     delight
    1.04
     awe
    0.98
     mesmer
    0.96
     unmatched
    0.96
     classics
    0.94
     envy
    0.94
     irresistible
    0.94
     thrill
    0.93
     enchant
    0.92
    Activations Density 0.579%

    No Known Activations