© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 4325
    Prev
    Next
    INDEX
    Explanations

    references to famous individuals and notable works in various fields such as psychology, history, philosophy, and chess

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

    references to historical figures and their 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
    ocom
    -0.60
     unloaded
    -0.59
    idine
    -0.58
    expensive
    -0.57
    glers
    -0.56
    amate
    -0.53
     overnight
    -0.53
     happ
    -0.53
    ezvous
    -0.53
    enegger
    -0.52
    POSITIVE LOGITS
     pp
    1.27
     §§
    1.16
     pg
    1.12
     chap
    1.09
     §
    1.05
     vol
    1.05
     iii
    1.01
     footnote
    1.00
    §
    0.97
     iv
    0.96
    Activations Density 0.206%

    No Known Activations