© 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. 13769
    Prev
    Next
    INDEX
    Explanations

    words related to past tense verbs ending in "-ed"

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "re" or words containing the prefix "re-"

    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
     faint
    -0.69
     gag
    -0.68
     Rabb
    -0.65
     Chinatown
    -0.64
     sourcing
    -0.62
     EntityItem
    -0.61
     Garfield
    -0.59
     Phar
    -0.59
     JPM
    -0.57
     reluct
    -0.57
    POSITIVE LOGITS
    cht
    1.21
    ngth
    1.15
    xit
    1.13
    bral
    1.12
    kson
    1.09
    asury
    1.08
    porter
    1.07
    versible
    1.07
    cks
    1.07
    gex
    1.02
    Activations Density 0.039%

    No Known Activations