© 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. 15908
    Prev
    Next
    INDEX
    Explanations

    mentions of significant actions or outcomes related to programming and software development

    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
    0:0.11
    1:0.10
    2:0.06
    3:0.06
    4:0.05
    5:0.04
    6:0.11
    7:0.13
    8:0.04
    9:0.03
    10:0.12
    11:0.09
    Negative Logits
     Croatian
    -3.10
     Booth
    -3.08
     Disapp
    -2.87
     Croatia
    -2.86
    の�
    -2.84
    ín
    -2.75
     Bennett
    -2.67
     Polk
    -2.61
     Sloven
    -2.57
     pav
    -2.56
    POSITIVE LOGITS
     regex
    6.61
    gex
    4.34
     coerc
    2.79
    pattern
    2.73
     grep
    2.65
    Regular
    2.63
    ?:
    2.57
     lex
    2.56
    =~
    2.55
     synt
    2.52
    Activations Density 0.000%

    No Known Activations