© 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. 0-RES-JB
    11. 1813
    Prev
    Next
    INDEX
    Explanations

    proper names and terms related to sports, specifically mentioning the Olympic Games

    oai_token-act-pair · gpt-3.5-turbo

    the name of a specific athlete

    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
     oppos
    -0.66
     mess
    -0.66
     Euro
    -0.62
     Serv
    -0.60
     circ
    -0.59
     else
    -0.59
     flour
    -0.57
     service
    -0.57
     Mag
    -0.57
     polar
    -0.57
    POSITIVE LOGITS
    hardt
    4.54
    hart
    1.65
    baugh
    1.45
    hard
    1.42
    hoff
    1.34
    heimer
    1.31
    lein
    1.27
    stadt
    1.23
    stein
    1.15
    enegger
    1.10
    Activations Density 0.004%

    No Known Activations