© 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. 15772
    Prev
    Next
    INDEX
    Explanations

    information related to a call for support or donations, specifically mentioning Patreon

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.09
    2:0.16
    3:0.07
    4:0.07
    5:0.07
    6:0.04
    7:0.04
    8:0.05
    9:0.19
    10:0.08
    11:0.03
    Negative Logits
    schild
    -1.53
     msec
    -1.41
    スト
    -1.33
    amba
    -1.32
     appar
    -1.32
    gun
    -1.30
    五
    -1.28
    Lenin
    -1.26
     elector
    -1.25
     trench
    -1.23
    POSITIVE LOGITS
     Patreon
    1.73
    reon
    1.56
    GG
    1.50
    outube
    1.40
     Ske
    1.40
    ═
    1.36
    Side
    1.36
    Creat
    1.34
    WT
    1.30
     incre
    1.28
    Activations Density 0.001%

    No Known Activations