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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6325
    Prev
    Next
    INDEX
    Explanations

    terms related to the fermentation process, specifically the presence of yeast

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fermentation and yeast processes

    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
     Hawk
    -0.84
    orget
    -0.83
    ukong
    -0.83
     Camer
    -0.77
     Razor
    -0.76
     Guns
    -0.76
    hawk
    -0.76
     Towers
    -0.75
     Gun
    -0.74
     Bears
    -0.74
    POSITIVE LOGITS
     ferment
    3.13
     fermentation
    3.12
     yeast
    2.83
     fermented
    2.58
     enzymes
    1.49
     brewer
    1.47
     enzyme
    1.42
     brewers
    1.42
     cider
    1.41
     ABV
    1.41
    Activations Density 0.048%

    No Known Activations