© 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. 9-RES-JB
    11. 23063
    Prev
    Next
    INDEX
    Explanations

    capitalized words separated by the letters 'l' and 's'

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific token or placeholder used in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICLE
    -0.69
     pleas
    -0.68
    ral
    -0.68
    bell
    -0.67
    rogens
    -0.66
    enegger
    -0.66
    ãģ®éŃĶ
    -0.65
    rises
    -0.62
     spirited
    -0.61
     Solitaire
    -0.61
    POSITIVE LOGITS
    ideshow
    1.31
    ippery
    1.29
    aughter
    1.18
    avery
    1.15
    oppy
    1.14
    aves
    1.09
    anguage
    1.09
    ashing
    1.08
    uggish
    1.07
    ippers
    1.07
    Activations Density 0.031%

    No Known Activations