© 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. 3889
    Prev
    Next
    INDEX
    Explanations

    references to political or legal actions involving individuals

    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
    0:0.10
    1:0.06
    2:0.09
    3:0.05
    4:0.02
    5:0.03
    6:0.14
    7:0.03
    8:0.02
    9:0.35
    10:0.04
    11:0.01
    Negative Logits
     Pyr
    -3.83
    PB
    -3.67
    iste
    -3.54
     Deb
    -3.49
     PB
    -3.45
    Psych
    -3.21
     Byte
    -3.18
     psychic
    -3.12
     Kemp
    -3.08
     Binary
    -3.07
    POSITIVE LOGITS
    Bring
    5.53
     Bring
    5.48
    bring
    5.46
     bring
    5.34
     brought
    4.68
    bringing
    4.59
     bringing
    4.51
     Liang
    3.99
     Bringing
    3.87
    rought
    3.81
    Activations Density 0.014%

    No Known Activations