© 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. 10-ATT-KK
    11. 16081
    Prev
    Next
    INDEX
    Explanations

    conditions or requirements related to participation or involvement in activities or events

    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
    0:0.04
    1:0.16
    2:0.05
    3:0.27
    4:0.04
    5:0.03
    6:0.04
    7:0.15
    8:0.04
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
    ワン
    -2.26
    nas
    -2.16
     unequ
    -2.13
     kan
    -2.12
    erity
    -2.05
     Valhalla
    -2.02
    ォ
    -1.97
    EngineDebug
    -1.95
    ゴ
    -1.93
     backgrounds
    -1.90
    POSITIVE LOGITS
    Late
    4.75
     late
    4.30
     Late
    4.28
    late
    3.63
    early
    2.26
    phis
    2.15
    Early
    2.12
     early
    2.10
    cious
    2.05
     foul
    2.04
    Activations Density 0.009%

    No Known Activations