© 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 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. 8486
    Prev
    Next
    INDEX
    Explanations

    phrases related to questions and inquiries, particularly those involving what is being asked

    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
    0:0.02
    1:0.49
    2:0.03
    3:0.05
    4:0.06
    5:0.03
    6:0.04
    7:0.06
    8:0.02
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
     fortnight
    -2.60
     Carbuncle
    -2.49
     mort
    -2.35
    elight
    -2.32
     misunder
    -2.27
    icult
    -2.25
     whom
    -2.19
    vier
    -2.18
    ild
    -2.13
    ague
    -2.12
    POSITIVE LOGITS
    that
    6.06
     that
    5.60
    That
    5.56
     That
    5.17
     THAT
    4.99
    those
    3.43
    Those
    3.38
     thats
    3.28
     those
    3.13
     Those
    3.12
    Activations Density 0.446%

    No Known Activations