© 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. 10-RES-JB
    11. 3358
    Prev
    Next
    INDEX
    Explanations

    ingredients and measurements in a recipe or cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements in cooking recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-
    -0.69
    hement
    -0.68
     exhausted
    -0.65
     citiz
    -0.63
     resid
    -0.63
     funer
    -0.62
     residences
    -0.60
     exha
    -0.58
     timely
    -0.58
     confir
    -0.58
    POSITIVE LOGITS
    ³³³
    0.94
    ³³³³³³³³³³³³³³³³
    0.94
    Instruct
    0.84
    ³³³³
    0.83
    ³³³³³³³³
    0.77
    ½
    0.77
    seed
    0.76
     ½
    0.75
    Optional
    0.75
    sea
    0.74
    Activations Density 0.026%

    No Known Activations