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. 0-RES-JB
    6. 21084
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "ky" at the end

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "ky" used in various contexts

    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
     Crus
    -0.64
     Curt
    -0.60
     dispos
    -0.58
     rapists
    -0.57
     caster
    -0.57
    REC
    -0.57
     cruc
    -0.56
     406
    -0.56
     damned
    -0.55
     Caleb
    -0.55
    POSITIVE LOGITS
    ky
    4.49
    kaya
    2.10
    ki
    2.08
    kies
    2.06
    KY
    1.97
    ker
    1.59
    ked
    1.56
    kers
    1.54
    king
    1.54
    ken
    1.54
    Activations Density 0.011%

    No Known Activations