Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9662
    Prev
    Next
    INDEX
    Explanations

    words in Swedish containing the character "ö"

    oai_token-act-pair · gpt-3.5-turbo

    the unique Swedish letter "ö"

    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
     entirety
    -0.73
     Kens
    -0.65
    aneous
    -0.65
     Cavaliers
    -0.65
    Subject
    -0.63
     degrade
    -0.63
    chair
    -0.62
     Corvette
    -0.61
     Deity
    -0.60
     Explain
    -0.60
    POSITIVE LOGITS
    ö
    1.47
    ä
    1.15
    ön
    1.13
    ü
    1.08
    ör
    0.98
    å
    0.97
    afia
    0.95
    zbek
    0.95
    hler
    0.95
    ÄŁ
    0.92
    Activations Density 0.005%

    No Known Activations