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. 1665
    Prev
    Next
    INDEX
    Explanations

    words related to Japanese cultural references

    oai_token-act-pair · gpt-3.5-turbo

    words related to a specific linguistic or cultural context, particularly involving the suffix "ese."

    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
    ãĥ¼ãĥĨ
    -0.84
    azine
    -0.82
    ilater
    -0.80
    razil
    -0.79
     Cumm
    -0.74
    ihar
    -0.74
     Kimber
    -0.73
    icals
    -0.70
    alist
    -0.69
    ific
    -0.68
    POSITIVE LOGITS
    ktop
    0.82
    uth
    0.76
    wei
    0.75
    lect
    0.71
    heng
    0.70
    clair
    0.69
    bones
    0.69
    userc
    0.68
    ese
    0.68
    vers
    0.67
    Activations Density 0.018%

    No Known Activations