© 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. 5-ATT-KK
    11. 43155
    Prev
    Next
    INDEX
    Explanations

    content related to sports events, particularly identifying teams and matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.12
    3:0.20
    4:0.21
    5:0.03
    6:0.05
    7:0.04
    8:0.05
    9:0.06
    10:0.07
    11:0.07
    Negative Logits
     ("
    -1.64
     altern
    -1.53
     coerc
    -1.47
     "{
    -1.39
    ��
    -1.36
     negatives
    -1.35
     salts
    -1.33
     encomp
    -1.33
    NetMessage
    -1.32
     associations
    -1.30
    POSITIVE LOGITS
    sic
    1.71
    ..."
    1.58
     #
    1.58
    pic
    1.50
    pedia
    1.47
     pic
    1.45
     @
    1.39
    wash
    1.38
     Rated
    1.38
    !".
    1.37
    Activations Density 0.028%

    No Known Activations