© 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. 1-RES-JB
    11. 9475
    Prev
    Next
    INDEX
    Explanations

    words related to veganism

    oai_token-act-pair · gpt-3.5-turbo

    references to veganism and vegan food

    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
    nings
    -0.76
    EMS
    -0.75
     Fargo
    -0.69
     Brow
    -0.68
     Powers
    -0.67
    older
    -0.67
    attr
    -0.66
    frames
    -0.64
     Gott
    -0.64
    ENCY
    -0.63
    POSITIVE LOGITS
     vegan
    1.04
     vegetarian
    0.94
    istani
    0.93
     Vegan
    0.89
     Nadu
    0.88
    ohydrate
    0.83
    iterranean
    0.78
    nesday
    0.78
    issan
    0.78
     chili
    0.78
    Activations Density 0.010%

    No Known Activations