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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44261
    Prev
    Next
    INDEX
    Explanations

    instances of approval and authorization related to legislation or regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.02
    2:0.06
    3:0.04
    4:0.22
    5:0.05
    6:0.02
    7:0.31
    8:0.03
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
    igi
    -1.62
    visible
    -1.46
    encers
    -1.46
    crow
    -1.43
    warts
    -1.41
    icken
    -1.41
    ulnerable
    -1.39
    luent
    -1.38
    bery
    -1.37
    lege
    -1.37
    POSITIVE LOGITS
     continuation
    1.58
     proposal
    1.54
     topp
    1.54
     bids
    1.53
     bid
    1.47
     shipment
    1.39
     shipments
    1.37
     proposals
    1.34
     annexation
    1.32
     bidding
    1.32
    Activations Density 0.008%

    No Known Activations