© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11721
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting symbols used in writing

    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
    0:0.06
    1:0.04
    2:0.05
    3:0.04
    4:0.07
    5:0.04
    6:0.17
    7:0.06
    8:0.08
    9:0.28
    10:0.02
    11:0.03
    Negative Logits
     bin
    -4.03
     Bin
    -3.93
    abase
    -3.92
     Eag
    -3.72
     bags
    -3.53
    deck
    -3.52
     bund
    -3.51
     phyl
    -3.48
     Sche
    -3.46
     bag
    -3.44
    POSITIVE LOGITS
     Knox
    8.97
    Tenn
    8.86
     Tennessee
    8.68
     TN
    7.05
     Tenn
    7.02
    essee
    5.65
     Nashville
    5.58
     Chattanooga
    5.40
     Corker
    5.08
     Titans
    4.96
    Activations Density 0.004%

    No Known Activations