© 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. 0-RES-JB
    11. 19196
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    references to film ratings and associated terms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    imar
    -0.80
    Mob
    -0.75
    appa
    -0.75
    Clar
    -0.69
     Racing
    -0.68
    icro
    -0.67
    car
    -0.67
     Mans
    -0.66
    atters
    -0.66
    Car
    -0.66
    POSITIVE LOGITS
     PG
    4.03
     SG
    1.57
     VG
    1.43
     PF
    1.25
     CG
    1.06
     MG
    1.04
     Nickel
    1.03
    VG
    1.01
    SG
    1.01
     Patty
    0.98
    Activations Density 0.042%

    No Known Activations