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. 5-ATT-KK
    6. 7422
    Prev
    Next
    INDEX
    Explanations

    references to legislative actions or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.13
    3:0.09
    4:0.14
    5:0.02
    6:0.05
    7:0.24
    8:0.04
    9:0.03
    10:0.09
    11:0.09
    Negative Logits
     realistically
    -1.30
     pores
    -1.27
     lining
    -1.23
     gust
    -1.19
     unthinkable
    -1.18
     yawn
    -1.18
     blink
    -1.17
     leaps
    -1.17
     cracks
    -1.17
     somew
    -1.15
    POSITIVE LOGITS
     Understanding
    1.27
     Xer
    1.26
    Compan
    1.26
    erva
    1.24
     Caesar
    1.20
     Raw
    1.19
    Critical
    1.18
     Wars
    1.18
     appell
    1.17
     Publication
    1.15
    Activations Density 0.053%

    No Known Activations