© 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. 11-RES-JB
    11. 18596
    Prev
    Next
    INDEX
    Explanations

    terms related to surveillance, especially issues surrounding data monitoring and privacy

    oai_token-act-pair · gpt-3.5-turbo

    references to surveillance and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubric
    -0.73
    ña
    -0.68
    mbol
    -0.67
    resents
    -0.65
     Piano
    -0.64
    oshi
    -0.64
     Reincarn
    -0.63
    interstitial
    -0.63
    ciating
    -0.62
     Centauri
    -0.61
    POSITIVE LOGITS
     programs
    1.04
     techniques
    1.01
     apparatus
    1.00
     programmes
    0.99
     capabilities
    0.99
     surveillance
    0.95
     technologies
    0.95
     powers
    0.94
     practices
    0.94
     operations
    0.94
    Activations Density 0.094%

    No Known Activations