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. 3-RES-JB
    6. 22063
    Prev
    Next
    INDEX
    Explanations

    words related to Uruguay

    oai_token-act-pair · gpt-3.5-turbo

    references to Uruguay and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trooper
    -0.78
    schild
    -0.71
    loss
    -0.71
     Catalog
    -0.69
     Marketplace
    -0.68
    dal
    -0.67
     trooper
    -0.67
    ais
    -0.64
    IZE
    -0.63
     counselor
    -0.62
    POSITIVE LOGITS
    cipl
    0.88
    uay
    0.81
     flick
    0.77
    dayName
    0.74
     Leonardo
    0.69
    aterasu
    0.69
     Uruguay
    0.68
    ury
    0.68
    drm
    0.67
    udic
    0.66
    Activations Density 0.024%

    No Known Activations