© 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. 19251
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements or quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to the number eighty

    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
    •Embedding Space Digit Features

    No Comments

    Negative Logits
     Nanto
    -0.74
    NetMessage
    -0.70
    jay
    -0.69
    inventoryQuantity
    -0.67
    wcsstore
    -0.66
    kay
    -0.65
    grave
    -0.65
     pri
    -0.64
    vere
    -0.62
    ary
    -0.62
    POSITIVE LOGITS
     80
    3.00
     70
    2.32
     90
    2.27
     85
    2.18
     81
    2.13
     75
    2.10
     82
    2.07
     78
    2.00
     60
    2.00
     84
    1.95
    Activations Density 0.037%

    No Known Activations