© 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. 8-RES-JB
    11. 9487
    Prev
    Next
    INDEX
    Explanations

    ingredients or food items related to veganism

    oai_token-act-pair · gpt-3.5-turbo

    mentions of veganism and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    witz
    -0.75
    hower
    -0.74
    frames
    -0.73
    etting
    -0.72
     lobe
    -0.71
    worthiness
    -0.70
    LER
    -0.69
    attr
    -0.68
    OPA
    -0.67
    manship
    -0.66
    POSITIVE LOGITS
    ism
    1.08
     diet
    0.94
    ohydrate
    0.91
     lifestyle
    0.88
     diets
    0.87
    ist
    0.87
     fatty
    0.86
    ization
    0.85
     foods
    0.84
     chili
    0.83
    Activations Density 0.034%

    No Known Activations