© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 20853
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "the" and other articles, conjunctions, and pronouns, indicating a focus on grammatical functions in the text

    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
    0:0.17
    1:0.02
    2:0.21
    3:0.05
    4:0.02
    5:0.08
    6:0.07
    7:0.04
    8:0.16
    9:0.07
    10:0.04
    11:0.02
    Negative Logits
    UFC
    -3.62
    ahon
    -3.50
     scrimmage
    -3.07
    cture
    -3.02
    黒
    -2.93
    brush
    -2.92
    ffen
    -2.91
    Iv
    -2.90
    lag
    -2.82
    ewater
    -2.81
    POSITIVE LOGITS
     SET
    5.78
    SET
    4.37
     interstellar
    3.54
     extrater
    3.45
     Hawking
    3.41
     Discovery
    3.40
     astroph
    3.25
     scientists
    3.18
     astronomer
    3.18
     signals
    3.17
    Activations Density 0.001%

    No Known Activations