© 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. 23864
    Prev
    Next
    INDEX
    Explanations

    reference to government institutions and their roles

    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
    1:0.02
    2:0.06
    3:0.07
    4:0.03
    5:0.03
    6:0.17
    7:0.03
    8:0.03
    9:0.34
    10:0.04
    11:0.05
    Negative Logits
     Kurd
    -3.73
     cann
    -3.66
     cannibal
    -3.65
     Idlib
    -3.53
     Croat
    -3.49
     Fernand
    -3.44
     Haf
    -3.43
     Wrest
    -3.41
     Cann
    -3.29
     Swift
    -3.29
    POSITIVE LOGITS
    office
    6.30
    Office
    6.26
     Office
    5.96
     offices
    5.83
     office
    5.65
    OPA
    3.81
    ahime
    3.80
     Oblivion
    3.76
     Headquarters
    3.62
     fixme
    3.51
    Activations Density 0.011%

    No Known Activations