© 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. 13055
    Prev
    Next
    INDEX
    Explanations

    references to specific political entities or projects, such as Keystone XL pipeline and Kathleen

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Keystone XL pipeline and associated figures

    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
    ideon
    -0.73
    ulia
    -0.70
    ista
    -0.68
    andum
    -0.68
    imental
    -0.67
    ersion
    -0.67
    ees
    -0.67
    driver
    -0.66
    FORE
    -0.66
    llor
    -0.66
    POSITIVE LOGITS
    bard
    1.10
    zos
    0.81
    rosse
    0.81
    ewater
    0.74
    JB
    0.69
     XL
    0.68
    email
    0.66
     Grain
    0.65
    quer
    0.65
     Amon
    0.62
    Activations Density 0.077%

    No Known Activations