© 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. 0-RES-JB
    11. 12144
    Prev
    Next
    INDEX
    Explanations

    locations and names in Spanish-speaking regions or countries

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or accent mark in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scant
    -0.62
     spread
    -0.61
     spreading
    -0.61
     scatter
    -0.60
     Kentucky
    -0.60
     leakage
    -0.59
     stealth
    -0.59
     circulation
    -0.58
     layout
    -0.58
     IM
    -0.58
    POSITIVE LOGITS
    ón
    4.73
    án
    1.86
    ão
    1.86
    ó
    1.83
    ÃŃn
    1.82
    ño
    1.57
    ú
    1.56
    ás
    1.55
    ÃŃa
    1.46
    és
    1.44
    Activations Density 0.022%

    No Known Activations