© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 19591
    Prev
    Next
    INDEX
    Explanations

    references to federal funding and support for marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.05
    3:0.10
    4:0.12
    5:0.29
    6:0.03
    7:0.03
    8:0.02
    9:0.19
    10:0.02
    11:0.05
    Negative Logits
    toggle
    -3.56
     downright
    -3.30
     fright
    -3.30
     lur
    -3.26
     tricked
    -3.23
     terrified
    -3.16
     ruined
    -3.10
     haha
    -3.10
     dude
    -3.10
     lonely
    -3.09
    POSITIVE LOGITS
     pursuant
    4.22
     envis
    3.76
     applicable
    3.69
     pertinent
    3.65
     relating
    3.60
    Footnote
    3.49
     comprising
    3.47
     relevant
    3.45
     undertaken
    3.44
     regarding
    3.42
    Activations Density 0.637%

    No Known Activations