© 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. 9-ATT-KK
    11. 17943
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and positive feedback towards products or experiences

    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
    0:0.11
    1:0.04
    2:0.09
    3:0.06
    4:0.26
    5:0.06
    6:0.03
    7:0.13
    8:0.04
    9:0.03
    10:0.04
    11:0.06
    Negative Logits
     displacement
    -2.31
    leneck
    -2.23
    Sym
    -2.23
    ntax
    -2.20
     scrut
    -2.18
    Types
    -2.10
    Definition
    -2.07
    lishes
    -2.06
     pits
    -2.01
    opes
    -2.00
    POSITIVE LOGITS
    Thank
    3.86
     THANK
    3.79
     Thank
    3.62
    thank
    3.42
     thank
    3.39
     Wonderful
    3.38
     Merry
    3.19
    Amazing
    2.79
     Thanks
    2.79
    Thanks
    2.77
    Activations Density 0.177%

    No Known Activations