© 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. 9-ATT-KK
    11. 15621
    Prev
    Next
    INDEX
    Explanations

    mentions of rankings, particularly in sports and other competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.03
    2:0.32
    3:0.09
    4:0.08
    5:0.09
    6:0.04
    7:0.06
    8:0.03
    9:0.03
    10:0.05
    11:0.02
    Negative Logits
     rupture
    -2.68
    displayText
    -2.60
     reusable
    -2.54
     interf
    -2.51
    dayName
    -2.43
     depos
    -2.41
     epid
    -2.38
     bonding
    -2.36
     reconnect
    -2.35
     rupt
    -2.34
    POSITIVE LOGITS
     rankings
    5.42
     Rankings
    5.21
     ranking
    5.09
     Ranking
    4.75
     ranked
    4.64
    Ranked
    4.19
    Rank
    4.15
     Ranked
    3.98
    ranked
    3.66
    rank
    3.51
    Activations Density 0.413%

    No Known Activations