© 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 EvalsExportsAPI 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. 3369
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms or articles

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas and quotation marks

    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
    Russ
    -0.58
    enta
    -0.57
    OND
    -0.57
    robe
    -0.56
     (>
    -0.55
     shenan
    -0.54
    worldly
    -0.53
    SPA
    -0.53
    ,
    -0.52
    ,—
    -0.50
    POSITIVE LOGITS
     involves
    1.18
     consists
    1.14
     revolves
    1.12
     comprises
    1.10
     represents
    1.07
     constitutes
    1.07
     is
    1.07
     relies
    1.04
     contains
    1.03
     allows
    1.03
    Activations Density 0.174%

    No Known Activations