© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20757
    Prev
    Next
    INDEX
    Explanations

    names of geographical locations, specifically focusing on cities such as Sheffield and Nottingham

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Sheffield

    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
    opsy
    -0.79
    onym
    -0.79
    osed
    -0.76
    ose
    -0.75
    oses
    -0.75
    cean
    -0.73
    ocr
    -0.71
    odore
    -0.71
    naire
    -0.70
     Genie
    -0.67
    POSITIVE LOGITS
     Sheffield
    1.34
    ffield
    0.99
    sburg
    0.83
     Watts
    0.74
     Slater
    0.74
     Peaks
    0.73
     Shields
    0.71
     Wyatt
    0.70
     Hanson
    0.69
    bridge
    0.69
    Activations Density 0.011%

    No Known Activations