© 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 EvalsExportsinterp-engineNEWAPI 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. 19053
    Prev
    Next
    INDEX
    Explanations

    sports teams and related news updates

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams and their activities

    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
     compan
    -0.75
    erb
    -0.68
    Britain
    -0.68
    compan
    -0.66
     advoc
    -0.64
     NGOs
    -0.64
    levels
    -0.64
    eln
    -0.63
    itbart
    -0.62
    hiba
    -0.62
    POSITIVE LOGITS
     preseason
    1.27
     Playoff
    1.27
     offseason
    1.27
     playoff
    1.25
     postseason
    1.15
     jerseys
    1.12
     roster
    1.12
     Playoffs
    1.08
     playoffs
    1.06
     rosters
    1.03
    Activations Density 0.541%

    No Known Activations