© 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 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. 2-RES-JB
    11. 22443
    Prev
    Next
    INDEX
    Explanations

    references to dark, evil, or supernatural entities such as Satan or Lucifer

    oai_token-act-pair · gpt-3.5-turbo

    references to Satan and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dropping
    -0.85
    enegger
    -0.83
    IGN
    -0.79
    RAFT
    -0.77
    dro
    -0.75
    ãģª
    -0.74
    drops
    -0.73
    --------------------------------------------------------
    -0.71
    ãģ¦
    -0.69
    ãĤī
    -0.68
    POSITIVE LOGITS
     incarn
    0.92
     worsh
    0.90
    istries
    0.83
    ism
    0.83
     Satan
    0.82
    alia
    0.79
    stration
    0.78
     worship
    0.78
    ashtra
    0.78
    isphere
    0.76
    Activations Density 0.010%

    No Known Activations