© 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. 11729
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating comparison or contrast

    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
    1:0.07
    2:0.12
    3:0.06
    4:0.03
    5:0.04
    6:0.20
    7:0.04
    8:0.03
    9:0.21
    10:0.05
    11:0.03
    Negative Logits
     Catalyst
    -3.74
    avez
    -3.72
     Catherine
    -3.53
     ●
    -3.42
    leased
    -3.23
    RAY
    -3.18
     Package
    -3.18
    Esc
    -3.17
     Chapel
    -3.15
     Reprodu
    -3.14
    POSITIVE LOGITS
     stupid
    6.29
     stupidity
    6.18
     dumb
    5.75
     idiots
    5.64
     Stupid
    5.64
     idiot
    5.05
     retarded
    4.68
     fools
    4.65
    upid
    4.57
     laz
    4.53
    Activations Density 0.006%

    No Known Activations