© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21015
    Prev
    Next
    INDEX
    Explanations

    references to previous blog posts, articles, or series

    oai_token-act-pair · gpt-3.5-turbo

    references to previously published articles or blog posts

    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
     plurality
    -0.65
     rebel
    -0.62
    ãĤ´ãĥ³
    -0.61
    forces
    -0.59
     Carbuncle
    -0.58
     holiest
    -0.58
    mson
    -0.57
    arov
    -0.56
     medd
    -0.55
    ousands
    -0.55
    POSITIVE LOGITS
     outlining
    1.09
     discussing
    1.09
     detailing
    1.07
     explaining
    1.06
     covering
    1.03
     entitled
    1.02
     titled
    0.99
     about
    0.99
    Introduction
    0.98
    mortem
    0.97
    Activations Density 0.205%

    No Known Activations