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. 7-RES-JB
    6. 2476
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations, with a focus on South Africa

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mech
    -0.75
    hower
    -0.72
    PATH
    -0.66
    naissance
    -0.66
    laden
    -0.66
    romeda
    -0.65
     cumbers
    -0.63
    cru
    -0.63
    mares
    -0.62
    Sense
    -0.60
    POSITIVE LOGITS
    tein
    0.80
     Mandela
    0.78
     Polic
    0.73
     Telecom
    0.70
     Presbyterian
    0.67
    atoon
    0.66
    ADA
    0.66
     Broadcasting
    0.66
    istan
    0.64
    à¥
    0.64
    Activations Density 0.064%

    No Known Activations