© 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. 4437
    Prev
    Next
    INDEX
    Explanations

    words related to specific geographic locations, specifically "Sioux" and "Civic"

    oai_token-act-pair · gpt-3.5-turbo

    specific names related to the Sioux tribe and the concept of civic engagement

    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
    lette
    -0.77
    etheless
    -0.77
     organising
    -0.71
     radiation
    -0.68
     destro
    -0.63
     Chern
    -0.61
     organise
    -0.61
    cki
    -0.61
     vaccination
    -0.60
     tiss
    -0.60
    POSITIVE LOGITS
    sie
    0.95
     Sioux
    0.83
     Falls
    0.79
    oux
    0.75
    lar
    0.73
    lon
    0.72
    rano
    0.72
    ivities
    0.72
    imating
    0.71
    ements
    0.71
    Activations Density 0.012%

    No Known Activations