© 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. 8-RES-JB
    11. 2756
    Prev
    Next
    INDEX
    Explanations

    locations or regions in England and Scotland

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amas
    -0.83
    Washington
    -0.83
    lando
    -0.83
    aturation
    -0.82
    ographed
    -0.81
    ILA
    -0.81
    ajor
    -0.79
    zona
    -0.78
    adena
    -0.77
    renheit
    -0.77
    POSITIVE LOGITS
     Borough
    1.19
    shire
    1.18
    £
    1.16
     £
    1.14
     Labour
    1.06
     Yorkshire
    1.04
     NHS
    1.03
     England
    1.01
     Ulster
    1.01
    hire
    1.01
    Activations Density 0.224%

    No Known Activations