© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    6. 1339
    Prev
    Next
    INDEX
    Explanations

    references to measurements or amounts of ingredients typically used in cooking

    oai_token-act-pair · gpt-3.5-turbo

    references to measuring cups in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.81
    Hunter
    -0.77
     Hunter
    -0.76
     Sands
    -0.76
     Hunters
    -0.73
     Surviv
    -0.73
     Investig
    -0.73
     Exploration
    -0.69
     Varg
    -0.69
     Jindal
    -0.69
    POSITIVE LOGITS
     cup
    3.68
     cups
    2.86
     Cup
    2.22
    cup
    2.13
     Cups
    2.03
     teaspoon
    1.44
     bowl
    1.40
     pint
    1.36
     tablespoon
    1.28
     coffee
    1.28
    Activations Density 0.006%

    No Known Activations