© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 5788
    Prev
    Next
    INDEX
    Explanations

    descriptions related to consuming or enjoying beverages

    oai_token-act-pair · gpt-3.5-turbo

    references to drinking or enjoying beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     morphology
    -0.80
     deform
    -0.76
     centers
    -0.75
    Site
    -0.73
    humans
    -0.70
     Centers
    -0.70
     vulnerabilities
    -0.70
    gypt
    -0.69
    ãĤ¨ãĥ«
    -0.68
     defects
    -0.68
    POSITIVE LOGITS
     drinks
    1.79
     drink
    1.66
     beverages
    1.64
     beers
    1.60
     cocktails
    1.58
     beverage
    1.57
     coffee
    1.56
     soda
    1.56
     beer
    1.53
     vodka
    1.51
    Activations Density 0.440%

    No Known Activations