© 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. 6713
    Prev
    Next
    INDEX
    Explanations

    discussions about financial and political dynamics involving media, technology, and governance

    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
    1:0.03
    2:0.05
    3:0.22
    4:0.03
    5:0.05
    6:0.02
    7:0.05
    8:0.02
    9:0.02
    10:0.40
    11:0.02
    Negative Logits
     thanking
    -2.33
    Thank
    -2.22
    farious
    -2.08
     applause
    -2.05
    ieu
    -2.04
     congratulations
    -1.99
     triumphant
    -1.96
     accol
    -1.95
    oward
    -1.92
     chorus
    -1.91
    POSITIVE LOGITS
     lacks
    3.49
     cannot
    2.71
     lacked
    2.68
     presupp
    2.51
     relies
    2.51
     isn
    2.40
     already
    2.39
     fundamentally
    2.38
     typically
    2.37
     lack
    2.37
    Activations Density 0.387%

    No Known Activations