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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 21862
    Prev
    Next
    INDEX
    Explanations

    mentions of specific African countries and political events or figures related to Africa

    oai_token-act-pair · gpt-3.5-turbo

    information related to conflicts and their impact in African countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Denver
    -1.09
     Rosenthal
    -0.93
    Apps
    -0.88
     Ghostbusters
    -0.88
    £ı
    -0.88
     Leafs
    -0.84
     Irving
    -0.82
     Gotham
    -0.81
    annabin
    -0.80
    Hamilton
    -0.80
    POSITIVE LOGITS
     Congo
    1.93
     Uganda
    1.88
     Rwanda
    1.83
     Angola
    1.78
     Liberia
    1.76
     Cameroon
    1.72
     Sudan
    1.72
     Kenya
    1.71
     Rw
    1.70
     Ug
    1.69
    Activations Density 0.464%

    No Known Activations