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. 2-RES-JB
    6. 24366
    Prev
    Next
    INDEX
    Explanations

    references to the continent of Africa

    oai_token-act-pair · gpt-3.5-turbo

    references to African people, culture, or topics related specifically to Africa

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORED
    -0.78
    IDER
    -0.72
     Perkins
    -0.71
    OPER
    -0.71
    INESS
    -0.70
    代
    -0.70
    ãģ®éŃĶ
    -0.70
     MFT
    -0.68
    士
    -0.68
    UTION
    -0.67
    POSITIVE LOGITS
    raid
    0.94
    eatures
    0.92
    wana
    0.92
    onso
    0.90
    rika
    0.87
    ghan
    0.82
    rica
    0.81
    rican
    0.80
    aren
    0.79
    riend
    0.79
    Activations Density 0.003%

    No Known Activations