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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10207
    Prev
    Next
    INDEX
    Explanations

    ingredients or foods commonly associated with recipes

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of nuts, beans, and other legumes in cooking and recipes

    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
     practition
    -0.69
    ONSORED
    -0.69
    minist
    -0.69
     circumstance
    -0.68
     maneuvers
    -0.68
    OWN
    -0.67
    ALLY
    -0.66
    eatures
    -0.66
    fare
    -0.66
     unification
    -0.65
    POSITIVE LOGITS
    mith
    1.14
    poons
    1.02
    pring
    1.00
    cape
    1.00
    kins
    0.99
    ilver
    0.98
    paces
    0.95
    cale
    0.94
    heet
    0.94
    hips
    0.93
    Activations Density 0.165%

    No Known Activations