© 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. 4-RES-JB
    11. 7404
    Prev
    Next
    INDEX
    Explanations

    information related to geographical locations, specifically focusing on England

    oai_token-act-pair · gpt-3.5-turbo

    mentions of England

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

    No Comments

    Negative Logits
    inventoryQuantity
    -0.83
    PsyNetMessage
    -0.76
    awaru
    -0.76
    yout
    -0.76
    henko
    -0.75
    onday
    -0.74
    dq
    -0.74
    ktop
    -0.71
    emonic
    -0.71
    heny
    -0.71
    POSITIVE LOGITS
    shire
    1.00
     Yard
    0.92
     Spit
    0.86
     Literature
    0.84
     Volunteers
    0.84
     Crown
    0.81
     Rugby
    0.80
     Defence
    0.77
    England
    0.76
    ury
    0.76
    Activations Density 0.009%

    No Known Activations