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. 19271
    Prev
    Next
    INDEX
    Explanations

    mentions of different cultures or civilizations

    oai_token-act-pair · gpt-3.5-turbo

    references to various cultures and their interactions

    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
    Phys
    -0.86
    ded
    -0.72
    thumbnails
    -0.69
     FML
    -0.69
    ZE
    -0.69
    Boy
    -0.68
    Software
    -0.67
    BN
    -0.67
    Guard
    -0.66
    odder
    -0.64
    POSITIVE LOGITS
    hops
    0.98
     civilizations
    0.96
    etter
    0.89
    poons
    0.89
    hips
    0.87
    cale
    0.85
    mith
    0.85
     cultures
    0.83
     empires
    0.79
     challeng
    0.79
    Activations Density 0.038%

    No Known Activations