© 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. 12574
    Prev
    Next
    INDEX
    Explanations

    mentions of the sports team "Houston Texans."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific sports teams, particularly the Houston Texans

    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
     Nigel
    -0.90
     Essex
    -0.87
     Cham
    -0.87
     Fletcher
    -0.85
     Glou
    -0.84
     Mog
    -0.76
     Simon
    -0.74
     Kitt
    -0.73
     Brighton
    -0.73
     Dodd
    -0.72
    POSITIVE LOGITS
     Texans
    3.32
     Astros
    2.72
     Rockets
    2.71
     Oilers
    1.99
     Dynamo
    1.98
    Houston
    1.78
     Houston
    1.69
     Harden
    1.65
    Tex
    1.51
     Jaguars
    1.43
    Activations Density 0.032%

    No Known Activations