© 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. 3-RES-JB
    11. 1836
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical regions or political entities like territories

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "territories," particularly in a geopolitical context

    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
    BOOK
    -0.77
    isma
    -0.72
    Bird
    -0.72
    ffer
    -0.71
    nder
    -0.71
    lder
    -0.68
    acha
    -0.67
    chard
    -0.66
    agher
    -0.65
    odcast
    -0.65
    POSITIVE LOGITS
    hips
    1.31
     Territories
    1.12
     territories
    0.96
    chool
    0.78
    hell
    0.78
     Territory
    0.78
    ystem
    0.75
    afety
    0.75
    hip
    0.73
    pec
    0.72
    Activations Density 0.010%

    No Known Activations