© 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. 14464
    Prev
    Next
    INDEX
    Explanations

    references to political themes and personal attacks related to current events

    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
    0:0.06
    1:0.02
    2:0.09
    3:0.11
    4:0.13
    5:0.11
    6:0.03
    7:0.28
    8:0.03
    9:0.02
    10:0.05
    11:0.02
    Negative Logits
    pora
    -2.25
    umption
    -1.99
     Shutterstock
    -1.99
    asca
    -1.99
    odi
    -1.98
    ernels
    -1.96
    umblr
    -1.96
    icates
    -1.93
     2048
    -1.89
    ズ
    -1.89
    POSITIVE LOGITS
     he
    3.73
    his
    3.57
     him
    3.50
     his
    3.39
    He
    3.35
     He
    3.03
    His
    3.03
    him
    2.94
     himself
    2.93
     replied
    2.86
    Activations Density 1.009%

    No Known Activations