© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 23176
    Prev
    Next
    INDEX
    Explanations

    references to countries being the largest in various aspects

    oai_token-act-pair · gpt-3.5-turbo

    superlative phrases indicating rankings or comparisons among countries or entities

    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
    mares
    -0.78
    acy
    -0.66
    hester
    -0.64
    enos
    -0.63
    eatures
    -0.63
    utations
    -0.62
    ouston
    -0.62
    eways
    -0.61
    Versions
    -0.61
    oops
    -0.61
    POSITIVE LOGITS
     largest
    1.32
     biggest
    1.26
     predominant
    1.12
     weakest
    1.11
     fastest
    1.10
     strongest
    1.08
     dominant
    1.08
     busiest
    1.08
     safest
    1.07
     heaviest
    1.07
    Activations Density 0.140%

    No Known Activations