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

    Neuronpedia

    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. 1-RES-JB
    11. 3817
    Prev
    Next
    INDEX
    Explanations

    terms related to beverages

    oai_token-act-pair · gpt-3.5-turbo

    terms related to beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orse
    -0.79
    urat
    -0.75
    arity
    -0.73
    awar
    -0.71
    inel
    -0.70
    idency
    -0.70
    ures
    -0.70
    ure
    -0.67
    iger
    -0.66
    igers
    -0.65
    POSITIVE LOGITS
     beverage
    1.40
     beverages
    1.40
     drinks
    1.20
    cohol
    1.07
     drinkers
    1.06
     drink
    1.00
     brewed
    0.99
     Drink
    0.98
     Bever
    0.95
     tasting
    0.91
    Activations Density 0.013%

    No Known Activations