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. 10427
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically related to popular tech frameworks like "Laravel" and "Django," as well as food items like "Parmesan Cheese."

    oai_token-act-pair · gpt-3.5-turbo

    specific references to names or brands, particularly those related to software or food

    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
    mith
    -0.77
    ^^^^
    -0.77
    iment
    -0.74
    ISH
    -0.72
     sidx
    -0.72
    ãĥĩãĤ£
    -0.71
    avorite
    -0.70
    eteria
    -0.67
    ^^
    -0.65
    hips
    -0.65
    POSITIVE LOGITS
     Raider
    0.76
    pas
    0.73
    atures
    0.71
     Keen
    0.70
    bits
    0.68
    atis
    0.68
    onomy
    0.68
     Armour
    0.68
    aci
    0.66
    acy
    0.65
    Activations Density 0.020%

    No Known Activations