© 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. 14305
    Prev
    Next
    INDEX
    Explanations

    numbers indicating quantities or quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to categorizations or classifications involving pairs or groups

    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
    someone
    -0.75
    ifice
    -0.74
    ighed
    -0.73
    endon
    -0.73
    $$
    -0.67
    esson
    -0.66
    annel
    -0.65
    Reviewed
    -0.65
    charge
    -0.65
    reb
    -0.64
    POSITIVE LOGITS
     types
    1.19
     kinds
    1.16
     distinct
    1.13
     phases
    1.13
     ways
    1.04
     main
    1.00
     tiers
    0.99
     different
    0.98
     stages
    0.97
     categories
    0.95
    Activations Density 0.163%

    No Known Activations