© 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. 12-RES-JB
    11. 5012
    Prev
    Next
    INDEX
    Explanations

    food-related terms, such as different types of eggs, slices of food, and subtle flavors

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    detailed descriptions and specific qualities related to food or textures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Cosponsors
    -0.64
    ourses
    -0.60
     veter
    -0.60
    Ĥİ
    -0.59
     Coliseum
    -0.58
    ullivan
    -0.57
    USS
    -0.57
    DES
    -0.57
     Halls
    -0.57
     vets
    -0.57
    POSITIVE LOGITS
     thereof
    1.05
     of
    1.00
    hower
    0.88
     glimps
    0.84
    berries
    0.79
    hered
    0.76
    iggle
    0.76
     sprinkled
    0.75
    bare
    0.75
     tucked
    0.73
    Activations Density 0.232%

    No Known Activations