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. 18558
    Prev
    Next
    INDEX
    Explanations

    names related to Brazilian politics

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to Brazilian politics and public figures

    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
    RIP
    -0.77
    cause
    -0.77
     Rider
    -0.75
    ancies
    -0.71
    ORE
    -0.70
    ################################
    -0.70
    sworth
    -0.69
    rake
    -0.69
    crew
    -0.69
    haar
    -0.68
    POSITIVE LOGITS
     Paulo
    1.12
     Jiu
    1.02
    inho
    1.01
     Janeiro
    0.94
     Portuguese
    0.88
     Silva
    0.84
    ão
    0.84
     Santos
    0.81
     Sao
    0.81
    ugal
    0.78
    Activations Density 0.018%

    No Known Activations