© 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. 18068
    Prev
    Next
    INDEX
    Explanations

    specific references to scientific and technical terminologies or proper nouns

    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
    0:0.08
    1:0.14
    2:0.06
    3:0.05
    4:0.04
    5:0.03
    6:0.13
    7:0.03
    8:0.06
    9:0.24
    10:0.02
    11:0.05
    Negative Logits
     Dek
    -3.61
    erk
    -3.02
     Cass
    -2.97
     Kend
    -2.91
    zik
    -2.88
    arist
    -2.87
    EY
    -2.79
     Mace
    -2.77
    eny
    -2.75
     Kan
    -2.75
    POSITIVE LOGITS
     IF
    6.34
    IF
    5.44
    PF
    3.99
    oub
    3.82
    ife
    3.82
    ief
    3.58
    gif
    3.49
     Gu
    3.49
     FP
    3.44
     PSP
    3.43
    Activations Density 0.001%

    No Known Activations