© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 17737
    Prev
    Next
    INDEX
    Explanations

    discussions about political pressure and human rights issues

    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
    0:0.04
    1:0.02
    2:0.08
    3:0.04
    4:0.08
    5:0.05
    6:0.16
    7:0.06
    8:0.13
    9:0.22
    10:0.01
    11:0.04
    Negative Logits
    ��極
    -3.47
     Meadow
    -3.46
     Gideon
    -3.46
     Hob
    -3.32
     bamboo
    -3.28
     glim
    -3.24
     cider
    -3.23
     Meadows
    -3.17
     bean
    -3.16
    Haw
    -3.15
    POSITIVE LOGITS
     Putin
    9.29
    Putin
    9.11
     Russians
    8.49
     Russia
    8.42
    Russia
    8.17
     Russian
    7.95
     Kremlin
    7.93
    Russian
    7.85
     Moscow
    7.85
    Moscow
    7.53
    Activations Density 0.078%

    No Known Activations