© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 24238
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and personal anecdotes

    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
    3:0.03
    4:0.05
    5:0.05
    6:0.20
    7:0.06
    8:0.10
    9:0.19
    10:0.02
    11:0.05
    Negative Logits
     cad
    -4.19
     martial
    -3.86
     Cisco
    -3.83
    gemony
    -3.77
    Interstitial
    -3.70
    deg
    -3.66
    vag
    -3.63
     Vag
    -3.36
    astery
    -3.33
    KC
    -3.29
    POSITIVE LOGITS
     Noah
    10.95
     Holt
    4.78
    Elsa
    4.34
     Antarctica
    4.24
     Nah
    4.23
    Isa
    4.20
     Elsa
    4.13
     Noel
    4.01
     Moses
    4.01
     Isaac
    3.97
    Activations Density 0.004%

    No Known Activations