© 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. 4788
    Prev
    Next
    INDEX
    Explanations

    personal names, advanced vocabulary, and biographical information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to books and published works

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    twitch
    -1.04
    ARA
    -0.79
     VIDEOS
    -0.72
    VC
    -0.72
    VK
    -0.71
     shenan
    -0.70
     twitch
    -0.70
    ansk
    -0.70
    wcs
    -0.69
    zik
    -0.69
    POSITIVE LOGITS
     paperback
    1.24
     published
    1.21
     edited
    1.08
     memoir
    1.08
     biography
    1.07
     reprint
    1.06
     Publishers
    1.03
     reprinted
    1.02
     autobiography
    1.01
    published
    1.00
    Activations Density 0.286%

    No Known Activations