© 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. 0-RES-JB
    11. 15422
    Prev
    Next
    INDEX
    Explanations

    words containing the subsequence "mark"

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of marking and identifying distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yson
    -0.89
    alf
    -0.75
     Cosponsors
    -0.70
     Lauder
    -0.65
     Kass
    -0.63
     Andrew
    -0.60
     bestselling
    -0.59
    âĹ¼
    -0.59
     lect
    -0.58
     gate
    -0.57
    POSITIVE LOGITS
    marked
    3.12
    marks
    2.03
    idy
    1.87
    eming
    1.05
    enic
    1.00
    iggle
    0.99
    oin
    0.89
    ivable
    0.88
    ozy
    0.88
     redeem
    0.86
    Activations Density 0.030%

    No Known Activations