© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 20538
    Prev
    Next
    INDEX
    Explanations

    German words containing the letter "ü"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character string "ü"

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ented
    -0.64
    orers
    -0.61
    enny
    -0.58
    eval
    -0.58
    avers
    -0.58
    ents
    -0.58
     Ballard
    -0.58
    ess
    -0.57
    ithing
    -0.57
    serving
    -0.56
    POSITIVE LOGITS
    ür
    1.17
    gency
    0.99
    ü
    0.95
    ãĥ³ãĤ¸
    0.82
    ÃĽ
    0.81
    gencies
    0.80
    ãĥĥ
    0.80
    gew
    0.78
     confir
    0.77
    nsic
    0.77
    Activations Density 0.005%

    No Known Activations