© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 11397
    Prev
    Next
    INDEX
    Explanations

    words related to stun guns and incidents involving stun guns

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.22
    3:0.07
    4:0.21
    5:0.06
    6:0.02
    7:0.03
    8:0.09
    9:0.11
    10:0.05
    11:0.03
    Negative Logits
    soDeliveryDate
    -1.79
    vernment
    -1.49
     Transactions
    -1.44
    soType
    -1.31
    govtrack
    -1.27
     Agric
    -1.22
    idences
    -1.21
    bern
    -1.21
    uid
    -1.20
     Confeder
    -1.19
    POSITIVE LOGITS
     boredom
    1.33
    bolt
    1.27
     Syndrome
    1.20
     syndrome
    1.20
    gui
    1.19
     tears
    1.17
     laughing
    1.15
    auga
    1.15
     humour
    1.15
    enment
    1.15
    Activations Density 0.002%

    No Known Activations