© 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. 2-RES-JB
    11. 17772
    Prev
    Next
    INDEX
    Explanations

    words related to Tibetan culture and politics

    oai_token-act-pair · gpt-3.5-turbo

    references to Tibet and its cultural or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.75
     Hitchcock
    -0.70
    ITY
    -0.68
    nesota
    -0.67
    ibus
    -0.67
    CLOSE
    -0.66
    adden
    -0.66
    eff
    -0.65
     posit
    -0.63
    rotein
    -0.62
    POSITIVE LOGITS
     Lama
    1.11
     Tibet
    1.07
     Buddhism
    0.99
     Buddhist
    0.98
     Tibetan
    0.97
    utan
    0.90
    istani
    0.88
     Buddh
    0.85
     pilgrims
    0.82
     monks
    0.80
    Activations Density 0.008%

    No Known Activations