© 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. 10-ATT-KK
    11. 8691
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.03
    2:0.12
    3:0.12
    4:0.15
    5:0.09
    6:0.04
    7:0.07
    8:0.05
    9:0.08
    10:0.04
    11:0.04
    Negative Logits
    achev
    -3.08
    ibrary
    -2.67
    '"
    -2.50
    )",
    -2.47
    kefeller
    -2.42
    ),"
    -2.42
     Rockefeller
    -2.41
    AIDS
    -2.40
     MBA
    -2.40
     ISBN
    -2.38
    POSITIVE LOGITS
    ··
    4.39
    �
    4.22
    ──
    3.95
    ─
    3.59
    ?」
    3.49
    �
    3.23
    ...?
    3.21
     �
    3.00
     �
    3.00
    ────
    3.00
    Activations Density 0.390%

    No Known Activations