© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11930
    Prev
    Next
    INDEX
    Explanations

    strategies and techniques related to combat and fighting

    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
    0:0.08
    1:0.03
    2:0.08
    3:0.13
    4:0.07
    5:0.10
    6:0.04
    7:0.09
    8:0.18
    9:0.04
    10:0.05
    11:0.06
    Negative Logits
    artifacts
    -2.86
     Lansing
    -2.71
     ML
    -2.67
    yrim
    -2.56
    �
    -2.47
     Pengu
    -2.35
     �
    -2.34
     GeForce
    -2.31
     FANTASY
    -2.30
     Michigan
    -2.30
    POSITIVE LOGITS
     clinch
    3.99
     Browne
    3.98
     takedown
    3.48
     McGregor
    3.26
     Thai
    3.24
     Rouse
    3.16
     boxing
    3.16
     MMA
    3.14
     jab
    3.12
     Silva
    3.07
    Activations Density 0.033%

    No Known Activations