© 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. 24227
    Prev
    Next
    INDEX
    Explanations

    instances of purchasing or subscription-related actions

    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
    3:0.10
    4:0.05
    5:0.11
    6:0.14
    7:0.08
    8:0.04
    9:0.21
    10:0.04
    11:0.08
    Negative Logits
     pirate
    -3.08
     rein
    -3.02
     Pirate
    -2.90
     piracy
    -2.83
     IG
    -2.80
     FO
    -2.74
     Cyprus
    -2.71
    finger
    -2.67
     bis
    -2.66
    Ry
    -2.65
    POSITIVE LOGITS
     Caption
    4.17
     sqor
    3.97
    actionDate
    3.82
    interstitial
    3.39
     Spr
    3.09
     Cosponsors
    2.98
     Array
    2.98
    CNN
    2.98
     Unloaded
    2.84
    raught
    2.84
    Activations Density 0.001%

    No Known Activations