© 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. 20399
    Prev
    Next
    INDEX
    Explanations

    references to various governments and countries

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "the government of" across various contexts

    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
    inventoryQuantity
    -0.80
     routines
    -0.69
     nightly
    -0.68
    fights
    -0.68
     volumes
    -0.68
     clos
    -0.67
     chops
    -0.66
     enthus
    -0.66
     strategies
    -0.64
     certs
    -0.63
    POSITIVE LOGITS
     Estonia
    1.33
     Yugoslavia
    1.32
     Canada
    1.22
     Kazakhstan
    1.22
     England
    1.20
     Ireland
    1.18
     Lithuania
    1.17
     Latvia
    1.16
     Albania
    1.15
     Finland
    1.15
    Activations Density 0.123%

    No Known Activations