© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 13100
    Prev
    Next
    INDEX
    Explanations

    specific sports-related terms and statistics, especially related to baseball and college football teams

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

    references to specific college sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.22
    1:0.05
    2:0.06
    3:0.04
    4:0.12
    5:0.05
    6:0.15
    7:0.05
    8:0.04
    9:0.03
    10:0.11
    11:0.05
    Negative Logits
     Etsy
    -1.29
    writing
    -1.26
    ographer
    -1.22
    ographic
    -1.20
    otomy
    -1.20
     Wikimedia
    -1.19
     TED
    -1.14
     Shutterstock
    -1.13
    ographers
    -1.13
     Brexit
    -1.08
    POSITIVE LOGITS
    Fan
    1.60
    SON
    1.23
     Jr
    1.19
     Stadium
    1.18
    IELD
    1.18
    lein
    1.16
    enhagen
    1.16
    gom
    1.14
    helps
    1.12
    Shield
    1.11
    Activations Density 0.052%

    No Known Activations