© 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. 11675
    Prev
    Next
    INDEX
    Explanations

    discussions about political issues and debates

    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
    1:0.03
    2:0.06
    3:0.20
    4:0.03
    5:0.12
    6:0.02
    7:0.10
    8:0.03
    9:0.02
    10:0.24
    11:0.03
    Negative Logits
     declined
    -2.07
    avorite
    -2.07
    mentioned
    -1.96
     disappeared
    -1.93
     vanished
    -1.88
     doubted
    -1.84
    weak
    -1.81
     forgot
    -1.80
    warn
    -1.80
     shouldn
    -1.80
    POSITIVE LOGITS
    xual
    2.18
     unfolding
    2.15
     embod
    2.04
     culmination
    2.02
    PRESS
    2.00
     orchestrated
    1.96
     grassroots
    1.93
     Purpose
    1.93
     leveraging
    1.91
     continuation
    1.89
    Activations Density 0.278%

    No Known Activations