© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14918
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and emotional engagement towards individuals 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
    0:0.03
    1:0.05
    2:0.06
    3:0.08
    4:0.17
    5:0.15
    6:0.05
    7:0.15
    8:0.03
    9:0.07
    10:0.06
    11:0.04
    Negative Logits
     pretended
    -2.76
     nonexistent
    -2.73
     cumbers
    -2.64
     bogus
    -2.60
     pretext
    -2.52
     faked
    -2.42
     pretending
    -2.39
     bystand
    -2.28
     purported
    -2.28
     Kills
    -2.24
    POSITIVE LOGITS
     will
    2.63
     appreciate
    2.56
     UNCLASSIFIED
    2.52
    �
    2.43
     continue
    2.42
     grate
    2.35
     THANK
    2.33
     welcomes
    2.31
     immensely
    2.24
     hopefully
    2.24
    Activations Density 0.211%

    No Known Activations