© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 14117
    Prev
    Next
    INDEX
    Explanations

    references to locations or entities with "Wil" in their names

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Wil."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Butterfly
    -0.85
    yrinth
    -0.75
    ģ«
    -0.73
    ograph
    -0.71
    chnology
    -0.66
    æĸ¹
    -0.65
     crush
    -0.65
    anwhile
    -0.63
    xual
    -0.63
    ographs
    -0.62
    POSITIVE LOGITS
    mot
    1.24
    cox
    1.17
    fred
    1.08
    lem
    1.06
    mington
    1.06
    ting
    1.03
    bur
    1.02
    ted
    1.01
    kes
    0.99
     Whe
    0.96
    Activations Density 0.025%

    No Known Activations