© 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. 3-RES-JB
    11. 3191
    Prev
    Next
    INDEX
    Explanations

    mentions related to tribal communities

    oai_token-act-pair · gpt-3.5-turbo

    references to tribal communities and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.76
    pherd
    -0.76
    mington
    -0.74
    ++++++++++++++++
    -0.72
    ppard
    -0.71
    aphael
    -0.71
    ————
    -0.71
    psons
    -0.70
    ffield
    -0.69
    eger
    -0.68
    POSITIVE LOGITS
     chiefs
    0.96
     tribal
    0.95
     affili
    0.90
     tribes
    0.84
     affiliation
    0.80
     elders
    0.79
    aida
    0.79
     councils
    0.79
     ancestry
    0.78
     Tribal
    0.77
    Activations Density 0.006%

    No Known Activations