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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1502
    Prev
    Next
    INDEX
    Explanations

    Scandinavian names or words containing the character "ö"

    oai_token-act-pair · gpt-3.5-turbo

    the word "för," which indicates discussions related to purpose or reason in Swedish

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Crusader
    -0.70
     Watson
    -0.69
     Bengal
    -0.66
    tons
    -0.66
    ORED
    -0.63
    INESS
    -0.62
     Sek
    -0.61
    corn
    -0.61
    enegger
    -0.60
     Blacks
    -0.60
    POSITIVE LOGITS
    andom
    1.12
    ör
    0.91
    ö
    0.90
    ð
    0.89
    onto
    0.83
    ön
    0.81
    án
    0.79
    ü
    0.79
    rent
    0.79
    istani
    0.77
    Activations Density 0.010%

    No Known Activations