Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 6350
    Prev
    Next
    INDEX
    Explanations

    words related to cooking spices

    oai_token-act-pair · gpt-3.5-turbo

    references to "spice" and related substances or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sters
    -0.79
    esis
    -0.73
    ston
    -0.71
    utral
    -0.70
    clipse
    -0.69
    istries
    -0.69
    ster
    -0.68
    sta
    -0.67
    enstein
    -0.67
    houses
    -0.67
    POSITIVE LOGITS
    endish
    0.77
    Cub
    0.74
    ense
    0.72
     Aires
    0.72
     spice
    0.71
    ATIVE
    0.71
    atile
    0.70
    ational
    0.69
    arse
    0.69
    abulary
    0.66
    Activations Density 0.088%

    No Known Activations