© 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. 4936
    Prev
    Next
    INDEX
    Explanations

    references to individuals, particularly in a political context

    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
    0:0.08
    1:0.02
    2:0.07
    3:0.03
    4:0.05
    5:0.03
    6:0.26
    7:0.04
    8:0.07
    9:0.25
    10:0.02
    11:0.03
    Negative Logits
     Levi
    -3.79
    Seg
    -3.53
    �
    -3.49
    �
    -3.31
     Wilkinson
    -3.25
     Huck
    -3.23
    aepernick
    -3.23
    ��
    -3.22
    roc
    -3.16
     IB
    -3.16
    POSITIVE LOGITS
    Mad
    9.29
     Mad
    8.41
     MAD
    7.95
    mad
    7.30
     Madonna
    6.41
     mad
    5.98
     Madd
    5.46
     Madame
    5.25
     Madness
    4.56
     Madagascar
    4.35
    Activations Density 0.006%

    No Known Activations