© 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. 11-RES-JB
    11. 22562
    Prev
    Next
    INDEX
    Explanations

    references to British-related terms or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals and events related to the UK

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Navajo
    -1.02
     canyon
    -0.91
     Coyotes
    -0.89
    zona
    -0.87
     pes
    -0.84
     salsa
    -0.84
     ng
    -0.82
    bernatorial
    -0.82
    aho
    -0.81
     DACA
    -0.81
    POSITIVE LOGITS
    Britain
    2.33
     Britain
    2.26
     Britons
    2.12
    London
    2.05
     London
    2.03
    England
    2.01
     British
    2.01
    British
    2.01
     UK
    1.98
     England
    1.96
    Activations Density 0.730%

    No Known Activations