© 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. 15986
    Prev
    Next
    INDEX
    Explanations

    Twitter handles starting with a person's first name, followed by their last name

    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
    0:0.06
    1:0.05
    2:0.05
    3:0.10
    4:0.03
    5:0.11
    6:0.11
    7:0.09
    8:0.08
    9:0.05
    10:0.14
    11:0.07
    Negative Logits
     orphans
    -1.14
    dfx
    -1.14
     inheritance
    -1.10
     alike
    -1.10
     duplication
    -1.08
     graft
    -1.04
     transsexual
    -1.01
     serotonin
    -1.00
    RGB
    -1.00
     substrate
    -0.99
    POSITIVE LOGITS
     (@
    1.56
    acher
    1.06
    rant
    1.06
    ンジ
    1.06
    enegger
    1.04
    ow
    1.03
    baugh
    1.03
    owski
    1.02
     Slov
    1.02
     �
    0.99
    Activations Density 0.026%

    No Known Activations