© 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. 7-RES-JB
    11. 23714
    Prev
    Next
    INDEX
    Explanations

    countries or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to countries and regions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oir
    -0.66
    isers
    -0.63
    orer
    -0.62
    iser
    -0.62
    jad
    -0.60
    ente
    -0.59
    ARCH
    -0.58
    thal
    -0.57
    EMBER
    -0.57
    ason
    -0.55
    POSITIVE LOGITS
    76561
    0.75
    ModLoader
    0.74
     Ele
    0.66
     livest
    0.65
     Carnage
    0.63
     Flavoring
    0.63
     Stronghold
    0.63
     Kard
    0.62
    otos
    0.62
     Minotaur
    0.61
    Activations Density 0.294%

    No Known Activations