© 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. 11-RES-JB
    11. 11312
    Prev
    Next
    INDEX
    Explanations

    phrases related to keeping information hidden or secret

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to secrecy and information being kept hidden

    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
    enegger
    -0.69
    ratulations
    -0.68
     Congratulations
    -0.66
    needed
    -0.63
    worms
    -0.60
     craving
    -0.59
     deserve
    -0.58
    racuse
    -0.58
     Chev
    -0.57
    ierre
    -0.57
    POSITIVE LOGITS
     secret
    1.30
     confidential
    1.08
     undisclosed
    1.03
     hidden
    1.02
    hidden
    1.02
     quiet
    0.98
     unpublished
    0.98
     shrouded
    0.98
     concealed
    0.94
     unpop
    0.94
    Activations Density 0.169%

    No Known Activations