© 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. 0-RES-JB
    11. 13001
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Things"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "Things" followed by various topics or issues

    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
     suite
    -0.66
     sponsor
    -0.65
    UAL
    -0.65
     blast
    -0.64
     mas
    -0.64
     permit
    -0.63
    adel
    -0.62
     cum
    -0.61
     circ
    -0.61
     scan
    -0.60
    POSITIVE LOGITS
     Things
    3.70
    Things
    2.92
    things
    2.40
     things
    1.95
     Thing
    1.88
     Stuff
    1.56
     Everything
    1.48
     Something
    1.47
    Something
    1.34
     Moments
    1.32
    Activations Density 0.011%

    No Known Activations