© 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. 12-RES-JB
    11. 3726
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and player positions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    details related to sports positions and formations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iev
    -0.85
     Transcript
    -0.84
    Poké
    -0.76
    Report
    -0.76
    Operation
    -0.75
    urious
    -0.75
    ðĿ
    -0.72
    ench
    -0.71
    chieve
    -0.70
    payers
    -0.70
    POSITIVE LOGITS
     fullback
    1.32
     wing
    1.16
     center
    1.10
     nickel
    1.10
     slot
    1.08
     midfield
    1.07
     shortstop
    1.03
     centre
    1.02
     winger
    1.01
     flank
    1.01
    Activations Density 0.220%

    No Known Activations