© 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. 13861
    Prev
    Next
    INDEX
    Explanations

    phrases related to secretive or sly actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to secrecy or stealth, particularly words involving "sneak" and its variations

    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
     Pwr
    -0.94
    oras
    -0.72
    minus
    -0.69
    pb
    -0.64
     Balanced
    -0.64
    main
    -0.62
    nil
    -0.62
    FontSize
    -0.60
    ucc
    -0.60
    ONT
    -0.60
    POSITIVE LOGITS
    ily
    1.24
     peek
    1.16
     sneak
    1.12
     glances
    1.01
     undet
    0.90
    door
    0.87
    ously
    0.86
     INTO
    0.84
     sneaking
    0.83
    away
    0.77
    Activations Density 0.084%

    No Known Activations