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. 4-RES-JB
    6. 3026
    Prev
    Next
    INDEX
    Explanations

    superlatives related to size and rank, such as "biggest", "largest", and ordinal numbers like "seventh" or "12th"

    oai_token-act-pair · gpt-3.5-turbo

    superlative forms indicating the world's largest or biggest entities

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

    No Comments

    Negative Logits
    isson
    -0.87
    chini
    -0.76
     Canaver
    -0.75
    arth
    -0.75
     Bullets
    -0.75
    fen
    -0.75
    metry
    -0.74
    utsu
    -0.73
    hawk
    -0.71
    phy
    -0.69
    POSITIVE LOGITS
     superpower
    0.81
     export
    0.74
     industrial
    0.72
     largest
    0.72
     flowering
    0.72
     international
    0.71
     internationally
    0.70
     exports
    0.69
     agricultural
    0.69
     industrialized
    0.69
    Activations Density 0.099%

    No Known Activations