© 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. 12241
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific characters that indicate dialogue or quotations

    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
    1:0.02
    2:0.06
    3:0.04
    4:0.05
    5:0.04
    6:0.31
    7:0.04
    8:0.07
    9:0.20
    10:0.02
    11:0.04
    Negative Logits
    igi
    -3.73
     Mazda
    -3.69
     Constantine
    -3.68
     Caesar
    -3.62
    Cath
    -3.57
    phi
    -3.54
    avis
    -3.44
     Magnum
    -3.44
     Kel
    -3.41
    obyl
    -3.40
    POSITIVE LOGITS
    Sw
    8.64
     Swanson
    8.26
     Sw
    7.78
    sw
    7.46
    SW
    7.40
     SW
    7.05
     sw
    6.38
     Swim
    5.89
     Swan
    5.67
     Swarm
    5.61
    Activations Density 0.014%

    No Known Activations