© 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. 2450
    Prev
    Next
    INDEX
    Explanations

    descriptions related to food and beverages

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

    descriptions of food and drink experiences

    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
     Sharif
    -0.80
    SpaceEngineers
    -0.73
     mosques
    -0.73
    Islam
    -0.73
     mosque
    -0.69
     Networks
    -0.67
     antennas
    -0.67
    roups
    -0.66
    ARP
    -0.66
     Islamists
    -0.65
    POSITIVE LOGITS
     drink
    1.51
     bottles
    1.49
     bottle
    1.47
    Bott
    1.45
     pour
    1.44
     Bottle
    1.43
     beverage
    1.40
     flask
    1.38
     drank
    1.37
     sip
    1.36
    Activations Density 0.424%

    No Known Activations