© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16952
    Prev
    Next
    INDEX
    Explanations

    phrases related to government surveillance and data collection

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government surveillance and privacy violations

    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
     Dise
    -0.73
    Adds
    -0.71
    Solution
    -0.71
     Disaster
    -0.70
    reci
    -0.66
     Monstrous
    -0.65
     restoration
    -0.62
     Fract
    -0.61
    iasis
    -0.61
    iculture
    -0.61
    POSITIVE LOGITS
     encrypted
    1.12
     communications
    1.11
     Gmail
    1.05
     telephone
    1.04
     phones
    1.04
     wiret
    1.04
     chats
    1.01
     conversations
    1.01
     eaves
    1.01
     phone
    0.99
    Activations Density 0.313%

    No Known Activations