© 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. 20905
    Prev
    Next
    INDEX
    Explanations

    publication dates or references in a text

    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
    0:0.03
    1:0.03
    2:0.04
    3:0.38
    4:0.04
    5:0.04
    6:0.03
    7:0.04
    8:0.21
    9:0.04
    10:0.03
    11:0.03
    Negative Logits
    /​
    -2.52
    •
    -2.45
    )—
    -2.34
    ••
    -2.32
    uca
    -2.31
     Move
    -2.25
    ¶
    -2.22
     Logged
    -2.19
    ).[
    -2.17
     Day
    -2.15
    POSITIVE LOGITS
    ahime
    2.36
    anyl
    2.32
    gart
    2.19
    Published
    2.17
    uyomi
    2.11
    akeru
    2.10
     hereby
    2.07
     actionGroup
    2.04
    odo
    2.04
    Santa
    2.04
    Activations Density 0.001%

    No Known Activations