© 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. 14495
    Prev
    Next
    INDEX
    Explanations

    names and locations

    oai_token-act-pair · gpt-3.5-turbo

    personal names or proper nouns in the text

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    hal
    -0.82
     turb
    -0.75
    122
    -0.72
     Karn
    -0.72
     radi
    -0.72
     Tob
    -0.72
     irrad
    -0.71
     Tara
    -0.71
     SF
    -0.70
     72
    -0.70
    POSITIVE LOGITS
    ie
    1.61
    iew
    1.22
    IE
    1.17
    ies
    1.13
    innie
    1.11
    iel
    1.10
    ied
    1.04
    iece
    1.03
    mie
    1.01
    orie
    1.00
    Activations Density 0.182%

    No Known Activations