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. 7034
    Prev
    Next
    INDEX
    Explanations

    key locations and establishments mentioned in the text

    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
    0:0.03
    1:0.02
    2:0.10
    3:0.06
    4:0.07
    5:0.04
    6:0.34
    7:0.03
    8:0.04
    9:0.04
    10:0.08
    11:0.11
    Negative Logits
     Ferdinand
    -1.37
     Hispan
    -1.37
     Eag
    -1.34
    arer
    -1.32
    hetically
    -1.31
    iru
    -1.31
    ater
    -1.31
     ashore
    -1.31
    ヘラ
    -1.27
    istine
    -1.27
    POSITIVE LOGITS
     Nex
    1.41
    gex
    1.34
     lobb
    1.32
    ggles
    1.31
     captcha
    1.29
    ophon
    1.28
     Javascript
    1.26
     Puzzles
    1.25
     Commons
    1.23
     CrossRef
    1.20
    Activations Density 0.001%

    No Known Activations