© 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. 21687
    Prev
    Next
    INDEX
    Explanations

    complex relationships or connections between 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
    0:0.07
    1:0.03
    2:0.07
    3:0.09
    4:0.03
    5:0.05
    6:0.05
    7:0.43
    8:0.03
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
     TIT
    -2.34
     Carly
    -2.27
     Cancel
    -2.24
     Sponsor
    -2.20
     Spons
    -2.16
    deal
    -2.16
     Prescott
    -2.13
     Britons
    -2.13
     tutor
    -2.10
     fav
    -2.10
    POSITIVE LOGITS
     improvis
    3.20
     individuality
    2.89
     exterior
    2.72
     horizontally
    2.69
     reusable
    2.68
     individual
    2.67
     spontaneous
    2.66
    assembly
    2.65
     ascending
    2.64
    outside
    2.63
    Activations Density 0.171%

    No Known Activations