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. 11-RES-JB
    6. 19430
    Prev
    Next
    INDEX
    Explanations

    financial and business terms

    oai_token-act-pair · gpt-3.5-turbo

    information pertaining to fast food restaurants and their promotional activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rhod
    -0.91
     moss
    -0.86
    agall
    -0.83
    yrim
    -0.81
     Ukrain
    -0.78
     Morrow
    -0.75
    emis
    -0.75
     sailing
    -0.73
    Storm
    -0.73
    afort
    -0.73
    POSITIVE LOGITS
     Burger
    2.08
     burger
    2.04
     Taco
    1.95
     McDonald
    1.90
     burgers
    1.89
     fries
    1.78
     hamb
    1.75
     Subway
    1.68
     taco
    1.56
     Wendy
    1.49
    Activations Density 0.350%

    No Known Activations