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

    Neuronpedia

    Jacobian LensNEW
    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. 9307
    Prev
    Next
    INDEX
    Explanations

    instances related to political and military dynamics, including protests, defense strategies, and agricultural business developments

    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
    0:0.09
    1:0.02
    2:0.06
    3:0.27
    4:0.02
    5:0.14
    6:0.02
    7:0.04
    8:0.04
    9:0.02
    10:0.22
    11:0.01
    Negative Logits
    inventoryQuantity
    -2.06
    released
    -2.00
    nesday
    -1.91
    specified
    -1.91
    IRED
    -1.87
    �醒
    -1.83
     TBA
    -1.81
     Valentine
    -1.77
    mentioned
    -1.76
    ));
    -1.75
    POSITIVE LOGITS
     empire
    2.35
     towers
    2.32
     bridges
    2.31
     tunnels
    2.23
     jails
    2.19
     empires
    2.13
     pipelines
    2.05
     railways
    2.04
     highways
    2.00
     arsenal
    2.00
    Activations Density 0.101%

    No Known Activations