© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14116
    Prev
    Next
    INDEX
    Explanations

    German foreign characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "ü."

    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
     Keeper
    -0.70
     Seas
    -0.69
    WHERE
    -0.67
     fracture
    -0.67
     Crush
    -0.63
    xon
    -0.63
     Crusher
    -0.62
     Raider
    -0.61
     ages
    -0.61
     charms
    -0.60
    POSITIVE LOGITS
    ü
    1.45
    ön
    0.93
    gency
    0.87
    ür
    0.87
    Ķ
    0.86
    ·
    0.85
    ez
    0.85
    uge
    0.85
    hl
    0.82
    eh
    0.82
    Activations Density 0.007%

    No Known Activations