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. 21717
    Prev
    Next
    INDEX
    Explanations

    terms related to extreme or high-intensity experiences or products

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Extreme" and related concepts

    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
    inson
    -0.74
    matically
    -0.71
    add
    -0.67
    yll
    -0.67
    rums
    -0.67
    omething
    -0.66
    olson
    -0.65
     externalToEVAOnly
    -0.65
    ¶æ
    -0.65
     tid
    -0.64
    POSITIVE LOGITS
     Edition
    1.04
     Packs
    1.04
     Warfare
    1.03
     Plus
    1.02
     Mode
    1.01
     Series
    1.00
     Catalog
    0.97
     Points
    0.95
     Cards
    0.94
     Rules
    0.94
    Activations Density 0.072%

    No Known Activations