© 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. 10-RES-JB
    11. 19066
    Prev
    Next
    INDEX
    Explanations

    the word "big" followed by a number ranging from 8 to 10

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "big."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Emin
    -0.75
    ILA
    -0.67
     largeDownload
    -0.67
     Reincarnated
    -0.66
    Reviewed
    -0.65
    ajor
    -0.64
    Dialogue
    -0.64
    DragonMagazine
    -0.63
     Technician
    -0.63
    icum
    -0.63
    POSITIVE LOGITS
    oted
    1.41
    wig
    1.09
    gest
    1.07
    gie
    1.07
    ger
    1.04
     bucks
    1.01
    ots
    1.01
    picture
    1.00
    amy
    0.99
     ol
    0.98
    Activations Density 0.064%

    No Known Activations