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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10704
    Prev
    Next
    INDEX
    Explanations

    phrases and vocabulary related to sports achievements and performances

    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
    0:0.03
    1:0.04
    2:0.04
    3:0.09
    4:0.10
    5:0.07
    6:0.02
    7:0.13
    8:0.08
    9:0.02
    10:0.28
    11:0.06
    Negative Logits
    cffff
    -2.47
    forums
    -2.18
    geist
    -2.15
    eworld
    -2.14
    milo
    -2.10
    Stud
    -2.09
    Studies
    -2.00
    %%%%
    -2.00
    ppelin
    -1.99
    Rare
    -1.97
    POSITIVE LOGITS
     afterward
    2.43
     goaltender
    2.27
     Nathan
    2.19
     afternoon
    2.18
     tying
    2.18
     defenseman
    2.09
     sealing
    2.04
     Leah
    2.02
     salv
    2.00
    ondo
    2.00
    Activations Density 0.075%

    No Known Activations