© 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. 10738
    Prev
    Next
    INDEX
    Explanations

    people who prefer to remain anonymous in sensitive situations

    oai_token-act-pair · gpt-3.5-turbo

    references to anonymity and the sensitive nature of information or situations

    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
    http
    -0.68
    HD
    -0.67
    ãĢIJ
    -0.67
    netflix
    -0.66
    liam
    -0.62
     Conquer
    -0.62
     Millennium
    -0.61
    chrome
    -0.61
     Avg
    -0.60
    animate
    -0.58
    POSITIVE LOGITS
     anonymity
    1.15
     confidentiality
    1.04
     sensitivity
    0.95
     privacy
    0.94
     confidential
    0.92
     sensit
    0.85
     repr
    0.83
     candid
    0.83
     sensitive
    0.78
     retribution
    0.77
    Activations Density 0.104%

    No Known Activations