© 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. 16043
    Prev
    Next
    INDEX
    Explanations

    information related to research studies and reports, especially those that have been commissioned by specific organizations

    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
    0:0.07
    1:0.03
    2:0.13
    3:0.08
    4:0.12
    5:0.05
    6:0.03
    7:0.02
    8:0.23
    9:0.13
    10:0.04
    11:0.02
    Negative Logits
    yip
    -1.51
    ihara
    -1.24
    touch
    -1.23
     Ashes
    -1.19
    aze
    -1.14
    hai
    -1.13
    ahime
    -1.13
     coma
    -1.12
    lycer
    -1.11
    ppo
    -1.10
    POSITIVE LOGITS
     scout
    1.22
     estimating
    1.21
     advising
    1.18
    earch
    1.17
    ORK
    1.14
     accredited
    1.09
    CDC
    1.09
     procurement
    1.08
     fundraising
    1.08
    PDATE
    1.08
    Activations Density 0.003%

    No Known Activations