© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 13465
    Prev
    Next
    INDEX
    Explanations

    numerical codes denoted by a special character followed by a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    instances of medical emergencies or related critical situations

    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
     eleph
    -0.90
     quir
    -0.75
     coral
    -0.75
     prosec
    -0.73
     excel
    -0.72
    yip
    -0.72
     oun
    -0.72
     metic
    -0.71
     predis
    -0.70
    xual
    -0.69
    POSITIVE LOGITS
    Eventually
    2.17
    Then
    2.05
    Soon
    2.00
    Later
    2.00
    Shortly
    1.94
    After
    1.86
    Within
    1.81
    Suddenly
    1.78
    Fast
    1.76
    Instead
    1.76
    Activations Density 0.487%

    No Known Activations