Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 37
    Prev
    Next
    INDEX
    Explanations

    references to specific years, particularly 2015 and 2016

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.04
    2:0.04
    3:0.10
    4:0.11
    5:0.23
    6:0.07
    7:0.11
    8:0.05
    9:0.01
    10:0.10
    11:0.04
    Negative Logits
     externalToEVAOnly
    -3.30
     graft
    -2.51
     spont
    -2.46
     サーティワン
    -2.40
     Roose
    -2.39
     pse
    -2.37
    .","
    -2.28
     deriv
    -2.27
     stump
    -2.26
     ende
    -2.25
    POSITIVE LOGITS
    Netflix
    2.71
    SPONSORED
    2.53
    etsy
    2.50
     gallery
    2.38
    Canada
    2.33
    UPDATE
    2.33
    audi
    2.25
    isons
    2.23
    Privacy
    2.21
     shut
    2.15
    Activations Density 0.011%

    No Known Activations