© 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. 1-RES-JB
    11. 3468
    Prev
    Next
    INDEX
    Explanations

    specific locations, especially focusing on the city "Damascus."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city Damascus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owler
    -0.86
    EEE
    -0.80
    OTT
    -0.77
    ographics
    -0.76
    rost
    -0.74
    Trend
    -0.74
    INAL
    -0.73
    RIP
    -0.72
    eu
    -0.72
    ramer
    -0.72
    POSITIVE LOGITS
    ascus
    1.30
     Damascus
    1.21
     rall
    0.91
     mosqu
    0.86
    ashtra
    0.85
     fingerprints
    0.74
     Assad
    0.73
     semblance
    0.73
    ²¾
    0.71
    atos
    0.70
    Activations Density 0.003%

    No Known Activations