© 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. 18737
    Prev
    Next
    INDEX
    Explanations

    phrases related to experience or quantity, specifically referring to various instances or amounts of something

    oai_token-act-pair · gpt-3.5-turbo
    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
    urden
    -0.73
    enance
    -0.70
    rium
    -0.67
    oyer
    -0.63
    etermined
    -0.62
    selection
    -0.60
    phia
    -0.60
     2020
    -0.60
     2030
    -0.59
    BILITY
    -0.59
    POSITIVE LOGITS
     iterations
    1.05
     incarn
    0.90
     occasions
    0.88
     editions
    0.87
     versions
    0.83
     lately
    0.83
     weddings
    0.82
     documentaries
    0.81
     civilizations
    0.80
     collaborations
    0.80
    Activations Density 0.179%

    No Known Activations