© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14289
    Prev
    Next
    INDEX
    Explanations

    descriptions of someone lying down

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lying" along with related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specialization
    -0.79
     tert
    -0.68
    ixel
    -0.64
    Ô
    -0.62
    Reviewer
    -0.61
     Explorer
    -0.60
    enty
    -0.59
    ellig
    -0.58
    ICO
    -0.58
    ozy
    -0.58
    POSITIVE LOGITS
     lifeless
    1.11
     slumped
    1.09
     unconscious
    1.09
     naked
    0.97
     knees
    0.96
     handcuffed
    0.96
     bleeding
    0.94
     face
    0.93
     limp
    0.93
     seiz
    0.92
    Activations Density 0.193%

    No Known Activations