© 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. 11415
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "buckle" in the text

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "knuckle."

    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
     Islamic
    -0.70
     Div
    -0.70
     ministry
    -0.66
     architect
    -0.65
     contest
    -0.65
     Quality
    -0.65
     scheduling
    -0.64
     secular
    -0.63
     quality
    -0.63
     modeling
    -0.63
    POSITIVE LOGITS
    uckle
    4.50
    uckles
    3.68
    uck
    1.30
    aughs
    1.13
    UCK
    1.09
    uble
    1.08
    ucket
    1.05
    uddy
    1.02
    ummer
    0.99
    ounge
    0.99
    Activations Density 0.015%

    No Known Activations