© 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. 18443
    Prev
    Next
    INDEX
    Explanations

    references to combat sports events and fighters

    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
    0:0.07
    1:0.02
    2:0.04
    3:0.15
    4:0.04
    5:0.05
    6:0.02
    7:0.08
    8:0.13
    9:0.03
    10:0.27
    11:0.04
    Negative Logits
    artifacts
    -2.41
     misinterpret
    -2.30
    productive
    -2.26
     errors
    -2.17
     mistakes
    -2.16
     miscar
    -2.04
     vandalism
    -1.99
     depreciation
    -1.99
     writings
    -1.99
     reprodu
    -1.96
    POSITIVE LOGITS
    henko
    2.76
     rematch
    2.44
     Typhoon
    2.43
     Mayweather
    2.41
     Diaz
    2.40
    uterte
    2.37
     Cage
    2.33
     Hogan
    2.31
     challenger
    2.30
     Cyborg
    2.28
    Activations Density 0.038%

    No Known Activations