© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12779
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their social interactions

    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
    2:0.09
    3:0.05
    4:0.04
    5:0.05
    6:0.22
    7:0.06
    8:0.07
    9:0.21
    10:0.03
    11:0.03
    Negative Logits
     Cad
    -4.05
     TD
    -4.05
     cad
    -3.61
    APD
    -3.59
    TD
    -3.53
     apples
    -3.49
     cuff
    -3.26
     Lego
    -3.18
     Guant
    -3.18
    FML
    -3.16
    POSITIVE LOGITS
     Shelley
    9.11
     Shel
    5.09
     Shiva
    4.46
     Shal
    4.40
     Slater
    4.37
     Byron
    4.33
     Frankenstein
    4.09
     Krishna
    4.04
     Shannon
    4.02
     Nev
    3.79
    Activations Density 0.001%

    No Known Activations