© 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. 14291
    Prev
    Next
    INDEX
    Explanations

    references to locations, especially in the context of political events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Saudi Arabia

    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
    matter
    -0.81
    chie
    -0.72
    oké
    -0.69
     {\
    -0.67
    early
    -0.66
    onym
    -0.66
    inventoryQuantity
    -0.65
    otin
    -0.65
    olving
    -0.64
    iven
    -0.64
    POSITIVE LOGITS
     Arabia
    1.78
     Arabian
    1.15
     Aram
    0.95
    ibaba
    0.87
     Airlines
    0.81
    anism
    0.81
    ansas
    0.79
     Senegal
    0.78
    ashtra
    0.78
     Royale
    0.78
    Activations Density 0.011%

    No Known Activations