© 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. 15628
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations, particularly focusing on the city of Damascus

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the cities Damascus and Cairo

    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
    owler
    -0.92
    Trend
    -0.79
    OTT
    -0.76
    opsy
    -0.75
    rost
    -0.75
    ocard
    -0.75
    lying
    -0.73
    unal
    -0.73
    rity
    -0.73
    INAL
    -0.73
    POSITIVE LOGITS
    ascus
    1.34
     Damascus
    1.04
     suburbs
    0.81
     Assad
    0.78
     rall
    0.78
    ites
    0.77
     mosqu
    0.75
    sels
    0.75
     suburb
    0.75
     countryside
    0.75
    Activations Density 0.006%

    No Known Activations