© 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. 8890
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and acknowledgment in texts

    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
    0:0.07
    1:0.08
    2:0.04
    3:0.06
    4:0.03
    5:0.03
    6:0.09
    7:0.37
    8:0.03
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
     Bern
    -2.95
     Braun
    -2.56
    ensen
    -2.49
    ケ
    -2.48
     Schwar
    -2.43
     Reich
    -2.42
    Bern
    -2.41
    ヴァ
    -2.40
     Bahrain
    -2.39
     Bucks
    -2.38
    POSITIVE LOGITS
    OPLE
    2.67
     UCHIJ
    2.46
    ��
    2.41
    isdom
    2.35
     anatomy
    2.35
    plom
    2.33
    orus
    2.30
    612
    2.28
     optic
    2.18
    dyl
    2.17
    Activations Density 0.006%

    No Known Activations