© 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. 11-RES-JB
    11. 3877
    Prev
    Next
    INDEX
    Explanations

    mentions of breweries and beer-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brewing industry and beer production details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -1.02
     Mubarak
    -0.88
    î
    -0.85
    hiba
    -0.81
    20439
    -0.80
     Mandela
    -0.78
    Egypt
    -0.78
     Makoto
    -0.77
     Zimbabwe
    -0.77
    uchin
    -0.77
    POSITIVE LOGITS
     breweries
    2.20
     brewery
    2.18
     brewers
    2.17
     beer
    2.13
    Beer
    2.13
     beers
    2.12
     brewer
    2.10
     brew
    2.09
    Brew
    2.07
     Beer
    2.05
    Activations Density 0.540%

    No Known Activations