© 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. 19063
    Prev
    Next
    INDEX
    Explanations

    definite articles and other common words

    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
    1:0.06
    2:0.11
    3:0.04
    4:0.07
    5:0.05
    6:0.13
    7:0.02
    8:0.04
    9:0.28
    10:0.03
    11:0.03
    Negative Logits
     Fas
    -3.45
    gob
    -3.33
    ECD
    -3.29
    ��
    -3.27
     Fren
    -3.24
    Gh
    -3.17
    ecd
    -3.16
     gib
    -3.12
    hog
    -3.06
     Runes
    -2.98
    POSITIVE LOGITS
     lawsuit
    6.53
     lawsuits
    6.33
     sue
    6.13
     sued
    6.10
     suing
    5.63
     suit
    5.42
     suits
    5.19
    suits
    5.17
     Suit
    5.00
     litigation
    4.64
    Activations Density 0.010%

    No Known Activations