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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7702
    Prev
    Next
    INDEX
    Explanations

    references to historical empires or civilizations, particularly focusing on their rise and fall

    oai_token-act-pair · gpt-3.5-turbo

    references to historical structures of power and civilization

    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
    inventoryQuantity
    -0.86
    ebin
    -0.83
    elight
    -0.83
    quickShipAvailable
    -0.77
    displayText
    -0.77
     needles
    -0.76
    soDeliveryDate
    -0.76
     referrals
    -0.72
    Lear
    -0.71
     Cosponsors
    -0.70
    POSITIVE LOGITS
     conquered
    1.15
     governed
    1.13
     collapsed
    1.03
     ruled
    1.03
     founded
    1.02
     flourished
    1.02
     disinteg
    1.02
     crumble
    1.01
     prosper
    1.01
     formed
    1.00
    Activations Density 0.224%

    No Known Activations