© 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. 9299
    Prev
    Next
    INDEX
    Explanations

    references to historical or collectible items, particularly rare books or recordings

    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
    0:0.12
    1:0.03
    2:0.14
    3:0.12
    4:0.08
    5:0.09
    6:0.06
    7:0.10
    8:0.09
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
    �
    -3.18
    Nusra
    -3.07
    amacare
    -3.04
    merga
    -3.03
     prioritize
    -2.88
    inki
    -2.86
    γ
    -2.86
    �
    -2.84
    onomous
    -2.69
    FML
    -2.67
    POSITIVE LOGITS
     1959
    3.88
     1963
    3.87
     1962
    3.86
     1938
    3.86
     1928
    3.86
     1939
    3.85
     1909
    3.83
     1912
    3.79
     Dickens
    3.78
     1897
    3.78
    Activations Density 0.405%

    No Known Activations