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. 7-ATT-KK
    6. 9521
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people, places, and sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.04
    2:0.07
    3:0.03
    4:0.05
    5:0.03
    6:0.03
    7:0.10
    8:0.03
    9:0.04
    10:0.06
    11:0.40
    Negative Logits
     STATS
    -2.35
    EStreamFrame
    -2.26
    ForgeModLoader
    -2.21
    ources
    -2.20
    Merit
    -2.18
     enthusi
    -2.18
    BuyableInstoreAndOnline
    -2.13
     pione
    -2.11
     Rohing
    -2.05
    OPLE
    -2.03
    POSITIVE LOGITS
    's
    5.01
    're
    3.89
    'd
    3.89
    '
    3.78
    'll
    3.65
    'm
    3.59
    't
    3.46
    '-
    3.39
    ′
    3.37
    ',"
    3.31
    Activations Density 0.012%

    No Known Activations