© 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. 4124
    Prev
    Next
    INDEX
    Explanations

    information pertaining to serious criminal events and legal implications

    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
    2:0.07
    3:0.02
    4:0.05
    5:0.02
    6:0.31
    7:0.04
    8:0.07
    9:0.21
    10:0.01
    11:0.03
    Negative Logits
     PIN
    -3.90
     "$:/
    -3.74
     Puzzles
    -3.57
    PIN
    -3.56
     CC
    -3.38
    onte
    -3.33
     IE
    -3.30
    anie
    -3.26
     Wiz
    -3.23
    avorite
    -3.22
    POSITIVE LOGITS
     Lamb
    12.24
     lamb
    8.30
     lambda
    5.43
    lambda
    5.22
     Lem
    4.65
    amb
    4.60
     Hamb
    4.56
     Lafayette
    4.43
     Lambert
    4.43
     Lam
    4.41
    Activations Density 0.002%

    No Known Activations