© 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. 3-ATT-KK
    11. 5309
    Prev
    Next
    INDEX
    Explanations

    terms related to identification and regulation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    terms related to identification and registration requirements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.06
    3:0.06
    4:0.03
    5:0.07
    6:0.10
    7:0.37
    8:0.04
    9:0.03
    10:0.09
    11:0.06
    Negative Logits
    Merit
    -1.31
    Offline
    -1.30
    antz
    -1.22
    姫
    -1.15
     sqor
    -1.14
     Mercenary
    -1.14
    NW
    -1.13
     Emin
    -1.10
    Engineers
    -1.10
     Views
    -1.09
    POSITIVE LOGITS
     clipboard
    1.42
     unlawfully
    1.14
     passport
    1.13
    elist
    1.09
     handy
    1.08
     Certificate
    1.08
     preferably
    1.06
     digitally
    1.04
     blacklist
    1.03
     caregivers
    1.03
    Activations Density 0.017%

    No Known Activations