© 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. 7-RES-JB
    11. 2894
    Prev
    Next
    INDEX
    Explanations

    locations in the UK

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations, specifically counties and regions in the UK

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onym
    -0.93
    aturation
    -0.83
    obin
    -0.79
    ogun
    -0.78
    inka
    -0.78
    amacare
    -0.78
    ographed
    -0.76
    zers
    -0.76
    endar
    -0.75
    vana
    -0.75
    POSITIVE LOGITS
    shire
    1.49
     Borough
    1.21
     County
    1.04
     Sussex
    1.01
    hire
    0.96
     Labour
    0.96
     Surrey
    0.94
     countryside
    0.93
     Ulster
    0.93
     Regiment
    0.93
    Activations Density 0.089%

    No Known Activations