© 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. 8-RES-JB
    11. 2621
    Prev
    Next
    INDEX
    Explanations

    terms related to stealth or hidden activities, such as stealthy characters, features, and skills

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stealth and assassination themes

    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
    artney
    -0.84
    anie
    -0.80
    ohyd
    -0.77
    inder
    -0.77
    inders
    -0.74
    atern
    -0.70
    bos
    -0.70
    zl
    -0.70
    ellar
    -0.70
    ONT
    -0.70
    POSITIVE LOGITS
    y
    0.86
    ily
    0.85
     Creed
    0.81
    IVE
    0.80
     Tactics
    0.78
     nomine
    0.74
    loo
    0.74
    ives
    0.70
     Assassins
    0.70
    ively
    0.70
    Activations Density 0.079%

    No Known Activations