© 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. 13113
    Prev
    Next
    INDEX
    Explanations

    references to a specific geographical location, mainland

    oai_token-act-pair · gpt-3.5-turbo

    references to "mainland" and related cardiovascular health factors

    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
    craft
    -0.84
    ster
    -0.82
    aciously
    -0.81
    ock
    -0.79
    ister
    -0.77
    nell
    -0.74
    anooga
    -0.73
    skirts
    -0.72
    adding
    -0.72
    oby
    -0.72
    POSITIVE LOGITS
    nces
    0.78
    xual
    0.70
     Sakuya
    0.69
     Advice
    0.69
     Welsh
    0.67
     redress
    0.65
    OPLE
    0.65
     Dhabi
    0.64
    ERO
    0.60
    iovascular
    0.60
    Activations Density 0.129%

    No Known Activations