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. 3-RES-JB
    6. 14424
    Prev
    Next
    INDEX
    Explanations

    words related to food items, particularly vegetables like pumpkin and squash

    oai_token-act-pair · gpt-3.5-turbo

    references to types of food, specifically pumpkins and squash

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lasses
    -0.74
    ugu
    -0.73
    eq
    -0.72
    stood
    -0.72
    rators
    -0.71
     Alam
    -0.70
    Reply
    -0.68
    nces
    -0.68
    gencies
    -0.66
    rets
    -0.64
    POSITIVE LOGITS
    fruit
    1.09
     pumpkin
    1.02
     spice
    0.94
     Pumpkin
    0.86
     pies
    0.82
     Spice
    0.82
     pie
    0.81
     juice
    0.77
    burg
    0.76
    head
    0.75
    Activations Density 0.007%

    No Known Activations