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. 14678
    Prev
    Next
    INDEX
    Explanations

    terms related to social class distinctions

    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
    0:0.03
    1:0.04
    2:0.03
    3:0.05
    4:0.07
    5:0.04
    6:0.04
    7:0.07
    8:0.03
    9:0.34
    10:0.04
    11:0.16
    Negative Logits
     VIDEOS
    -2.59
     Announce
    -2.50
    igate
    -2.48
     giveaway
    -2.34
     vomit
    -2.20
     kiss
    -2.19
     apologize
    -2.19
     apologise
    -2.18
     sneak
    -2.17
     accompany
    -2.14
    POSITIVE LOGITS
    iors
    3.04
     incomes
    2.58
    ippers
    2.51
    types
    2.46
    average
    2.39
    vals
    2.37
     generations
    2.31
     populations
    2.29
    oters
    2.29
    ustomed
    2.27
    Activations Density 0.006%

    No Known Activations