© 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. 9-ATT-KK
    11. 13162
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols that may indicate emotional or dramatic emphasis

    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
    0:0.08
    1:0.02
    2:0.08
    3:0.04
    4:0.05
    5:0.04
    6:0.22
    7:0.06
    8:0.06
    9:0.23
    10:0.04
    11:0.04
    Negative Logits
    iano
    -4.36
     Rice
    -4.32
     Oman
    -3.77
     McCorm
    -3.74
    uri
    -3.58
     Coral
    -3.56
    moon
    -3.51
     Flowers
    -3.45
     Cosmos
    -3.36
     Ri
    -3.35
    POSITIVE LOGITS
     Zach
    8.73
     Zack
    6.38
     Zac
    4.08
     bash
    3.85
     buckets
    3.80
     Volt
    3.70
    Jess
    3.56
     bucket
    3.52
     skate
    3.50
     Zak
    3.45
    Activations Density 0.000%

    No Known Activations