© 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. 0-RES-JB
    11. 19138
    Prev
    Next
    INDEX
    Explanations

    mentions of privacy-related terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stri
    -0.76
    ski
    -0.72
    hit
    -0.68
     Disciple
    -0.68
    itzer
    -0.66
    eous
    -0.66
     Brothers
    -0.66
    axis
    -0.64
    Wars
    -0.64
    saw
    -0.63
    POSITIVE LOGITS
     privacy
    4.07
     Privacy
    2.77
    Privacy
    2.66
     confidentiality
    2.08
     anonymity
    2.03
     secrecy
    1.76
     transparency
    1.40
    priv
    1.37
     modesty
    1.36
     anonym
    1.31
    Activations Density 0.026%

    No Known Activations