© 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. 20840
    Prev
    Next
    INDEX
    Explanations

    references to individual experiences and knowledge about specific people or concepts

    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
    1:0.03
    2:0.03
    3:0.13
    4:0.02
    5:0.08
    6:0.01
    7:0.07
    8:0.02
    9:0.01
    10:0.48
    11:0.02
    Negative Logits
    ín
    -2.20
    onding
    -1.81
    TRY
    -1.77
    ursday
    -1.75
    lication
    -1.72
    nesday
    -1.68
     seeking
    -1.67
    ousing
    -1.66
     attempting
    -1.62
    cellaneous
    -1.61
    POSITIVE LOGITS
     intimately
    2.34
     anecd
    2.17
     dearly
    2.02
     better
    1.92
     firsthand
    1.86
    kamp
    1.85
     knows
    1.82
    better
    1.81
     already
    1.80
     basics
    1.74
    Activations Density 0.237%

    No Known Activations