© 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. 703
    Prev
    Next
    INDEX
    Explanations

    references to Indigenous peoples and communities

    oai_token-act-pair · gpt-3.5-turbo

    references to Indigenous and Aboriginal peoples and related topics

    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
    ueller
    -0.88
    orious
    -0.87
     Oswald
    -0.75
    ãĥ´ãĤ¡
    -0.75
    eus
    -0.75
    ilion
    -0.74
     Nero
    -0.72
    oldemort
    -0.71
     Kramer
    -0.71
    isSpecialOrderable
    -0.70
    POSITIVE LOGITS
     peoples
    1.22
     Peoples
    1.13
     tribes
    1.13
     tribe
    1.04
     Nations
    1.04
     communities
    0.99
     Tribal
    0.99
     Nation
    0.97
     elders
    0.96
     tribal
    0.96
    Activations Density 0.096%

    No Known Activations