© 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. 1-RES-JB
    11. 10216
    Prev
    Next
    INDEX
    Explanations

    mentions of the region Tibet

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Tibet and related cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.70
    hift
    -0.65
    RH
    -0.62
    ctive
    -0.61
    FACE
    -0.61
     Hitchcock
    -0.61
    eff
    -0.61
    ________
    -0.61
    ISTER
    -0.60
    ITY
    -0.60
    POSITIVE LOGITS
     Tibet
    1.11
     Buddhism
    0.90
     pilgrims
    0.88
    utan
    0.85
     Rohing
    0.81
     Tibetan
    0.80
     Nadu
    0.79
     Buddh
    0.77
    agna
    0.77
     Buddhist
    0.76
    Activations Density 0.005%

    No Known Activations