© 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. 579
    Prev
    Next
    INDEX
    Explanations

    punctuation and certain grammatical structures in the text

    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
    0:0.10
    1:0.02
    2:0.05
    3:0.04
    4:0.03
    5:0.03
    6:0.22
    7:0.04
    8:0.06
    9:0.27
    10:0.04
    11:0.04
    Negative Logits
     Carm
    -4.23
     Mellon
    -3.85
    gem
    -3.80
     Lloyd
    -3.66
     Oliv
    -3.56
     peach
    -3.46
     Elliott
    -3.37
    icker
    -3.24
    angel
    -3.22
    kl
    -3.21
    POSITIVE LOGITS
     Sur
    8.57
    Sur
    6.36
    sur
    6.21
     SUR
    5.92
     sur
    5.51
     SAR
    5.36
     Surf
    4.91
     surfing
    4.84
     surf
    4.49
     Lur
    4.02
    Activations Density 0.001%

    No Known Activations