© 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. 16853
    Prev
    Next
    INDEX
    Explanations

    instances of the word "we" and variations of "the" and "cleared."

    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
    0:0.10
    1:0.08
    2:0.09
    3:0.03
    4:0.03
    5:0.04
    6:0.16
    7:0.04
    8:0.03
    9:0.29
    10:0.03
    11:0.02
    Negative Logits
    gres
    -3.49
    iga
    -3.27
    ______
    -3.24
    von
    -3.21
     Horowitz
    -3.17
    JO
    -3.17
     Musical
    -3.16
     IG
    -3.13
     Mik
    -3.12
    IU
    -3.06
    POSITIVE LOGITS
     Clear
    6.84
    Clear
    6.49
    clear
    6.06
    Cle
    5.42
     CLE
    5.39
     clearance
    5.25
     clears
    5.15
     Cle
    5.05
     clearing
    4.99
     clear
    4.92
    Activations Density 0.002%

    No Known Activations