© 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. 3-RES-JB
    11. 5108
    Prev
    Next
    INDEX
    Explanations

    food and cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cooking and food preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gamergate
    -0.81
     Rosenstein
    -0.69
     GamerGate
    -0.67
     advers
    -0.67
     Kissinger
    -0.66
    vind
    -0.66
     Elections
    -0.64
     wrongful
    -0.64
     secession
    -0.63
     ISIL
    -0.63
    POSITIVE LOGITS
     creamy
    0.90
     aroma
    0.85
     moisture
    0.81
     stocking
    0.79
     texture
    0.79
     refill
    0.79
     waterproof
    0.78
     freezer
    0.77
     powd
    0.76
     moistur
    0.75
    Activations Density 2.067%

    No Known Activations