© 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. 0-RES-JB
    11. 9658
    Prev
    Next
    INDEX
    Explanations

    mentions of different breweries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of brewing companies and breweries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     monitor
    -0.72
     bodies
    -0.69
     routine
    -0.67
     ser
    -0.66
     tele
    -0.66
     spare
    -0.65
     dummy
    -0.65
     mon
    -0.63
     pole
    -0.63
    sheet
    -0.63
    POSITIVE LOGITS
     Brewing
    3.84
     Brewery
    2.32
    Brew
    1.98
     brewing
    1.80
     brewery
    1.67
     Brew
    1.67
     brewed
    1.63
     Beer
    1.60
     breweries
    1.59
    brew
    1.58
    Activations Density 0.023%

    No Known Activations