© 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
    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. 8599
    Prev
    Next
    INDEX
    Explanations

    specific labels or identifiers such as "Thumbnails" and dates in a particular format (e.g., April 9) in a document

    oai_token-act-pair · gpt-3.5-turbo

    numeric data and references to dates or measurements

    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
     Taj
    -0.81
     Alberto
    -0.78
     Derrick
    -0.74
     ASIC
    -0.74
     Sunderland
    -0.71
     Bas
    -0.70
     Tra
    -0.69
     Rudolph
    -0.69
     1932
    -0.69
    erman
    -0.69
    POSITIVE LOGITS
    5
    1.44
     5
    1.43
    five
    1.10
     Five
    1.07
     Fifth
    1.02
     five
    0.99
    Five
    0.91
    fifth
    0.91
     fifth
    0.89
     525
    0.89
    Activations Density 0.186%

    No Known Activations