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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14668
    Prev
    Next
    INDEX
    Explanations

    references to organizations and initiatives related to the arts and culture

    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
    0:0.04
    1:0.05
    2:0.10
    3:0.07
    4:0.06
    5:0.17
    6:0.08
    7:0.05
    8:0.04
    9:0.16
    10:0.08
    11:0.05
    Negative Logits
     skelet
    -2.49
     tracks
    -2.24
     ultras
    -2.21
     TX
    -2.15
     replicate
    -2.12
     depri
    -2.11
     indicating
    -2.07
     trains
    -2.06
     packs
    -2.06
     whichever
    -2.06
    POSITIVE LOGITS
    DragonMagazine
    2.77
    elcome
    2.68
    VICE
    2.54
    romeda
    2.53
    ="/
    2.49
    gency
    2.44
    ueller
    2.38
    umbn
    2.36
    iframe
    2.36
    mare
    2.34
    Activations Density 0.005%

    No Known Activations