© 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. 425
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific sound patterns or phonetic elements in 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
    0:0.04
    1:0.02
    2:0.03
    3:0.05
    4:0.03
    5:0.03
    6:0.13
    7:0.02
    8:0.03
    9:0.51
    10:0.02
    11:0.03
    Negative Logits
     Willis
    -5.07
     Wynne
    -3.67
     Polk
    -3.49
     Von
    -3.34
     Jenna
    -3.29
     neutron
    -3.26
     Thermal
    -3.26
     Corn
    -3.25
     Mel
    -3.23
     Ther
    -3.22
    POSITIVE LOGITS
    ag
    6.49
    ags
    6.35
    AG
    6.01
    og
    5.83
    OG
    5.42
    agg
    5.38
    IG
    5.34
     Og
    5.32
    ig
    5.22
    agging
    5.21
    Activations Density 0.181%

    No Known Activations