© 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. 9-ATT-KK
    11. 20766
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and requests for further action

    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
    2:0.07
    3:0.05
    4:0.29
    5:0.13
    6:0.03
    7:0.08
    8:0.04
    9:0.02
    10:0.07
    11:0.01
    Negative Logits
    imentary
    -2.56
    ournament
    -2.34
     repr
    -2.21
    ipel
    -2.17
    phe
    -2.14
    plementation
    -2.13
     portrait
    -2.13
    �
    -2.08
    pter
    -2.06
    agon
    -2.06
    POSITIVE LOGITS
    mad
    2.64
     Wow
    2.50
     Ah
    2.50
     Thinking
    2.42
    tis
    2.36
     We
    2.33
     Believe
    2.32
     Okay
    2.28
     Lets
    2.26
     Uh
    2.25
    Activations Density 0.002%

    No Known Activations