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

    Neuronpedia

    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. 9-ATT-KK
    11. 10896
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and events

    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
    0:0.03
    1:0.11
    2:0.04
    3:0.04
    4:0.02
    5:0.04
    6:0.08
    7:0.02
    8:0.02
    9:0.48
    10:0.03
    11:0.04
    Negative Logits
    �
    -3.32
     Mic
    -3.28
     turtles
    -3.10
    STDOUT
    -3.03
    urtles
    -2.92
    ......
    -2.88
    Mic
    -2.88
     turtle
    -2.87
     Turtles
    -2.87
     sidel
    -2.86
    POSITIVE LOGITS
     21
    5.63
    21
    5.54
     1921
    4.72
    021
    4.44
     51
    4.39
    71
    4.34
     221
    4.27
     181
    4.24
    51
    4.18
     91
    4.17
    Activations Density 0.024%

    No Known Activations