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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 11699
    Prev
    Next
    INDEX
    Explanations

    references to privacy or privilege

    oai_token-act-pair · gpt-3.5-turbo

    references to privacy and private information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IELD
    -0.73
     Zucker
    -0.69
     dividing
    -0.63
    ers
    -0.62
    ered
    -0.62
     Pixie
    -0.62
    ORN
    -0.61
     Ducks
    -0.60
    ering
    -0.60
     pointing
    -0.60
    POSITIVE LOGITS
    ilege
    1.47
    ileged
    1.40
    acies
    1.37
    acy
    1.22
    atism
    1.14
    atis
    1.11
    abulary
    1.08
    acists
    1.03
    ately
    1.02
    atically
    1.01
    Activations Density 0.061%

    No Known Activations