© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 19157
    Prev
    Next
    INDEX
    Explanations

    mentions of players and coaching staff related to the New York Islanders

    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
    0:0.06
    1:0.02
    2:0.05
    3:0.09
    4:0.05
    5:0.06
    6:0.08
    7:0.07
    8:0.31
    9:0.06
    10:0.07
    11:0.04
    Negative Logits
    ─
    -3.34
    �
    -3.18
    xual
    -3.10
     Zimbabwe
    -3.06
     Lyon
    -3.02
    ğ
    -3.00
     Cameroon
    -2.95
     Mosul
    -2.94
    aghd
    -2.92
     Birmingham
    -2.92
    POSITIVE LOGITS
     Islanders
    6.47
     Staten
    5.13
     Nass
    4.70
     Isles
    4.59
     Brooklyn
    4.28
     Albany
    4.27
     Island
    4.17
     Sweeney
    3.98
     Niagara
    3.95
     NY
    3.89
    Activations Density 0.004%

    No Known Activations