© 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. 2309
    Prev
    Next
    INDEX
    Explanations

    connections between characters in comic book universes, particularly involving villains

    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
    1:0.02
    2:0.05
    3:0.02
    4:0.05
    5:0.04
    6:0.20
    7:0.04
    8:0.04
    9:0.33
    10:0.03
    11:0.02
    Negative Logits
     Severus
    -4.09
     Guan
    -3.76
     Sasuke
    -3.63
     Grayson
    -3.47
     Ve
    -3.38
     Lily
    -3.37
    vg
    -3.36
     Ced
    -3.36
    ilib
    -3.35
     vert
    -3.33
    POSITIVE LOGITS
     Radio
    9.00
    Radio
    8.83
    radio
    8.16
     radio
    8.05
     radios
    7.27
     RAD
    5.13
     RF
    4.84
     FM
    4.78
    RF
    4.50
     radioactive
    4.40
    Activations Density 0.010%

    No Known Activations