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. 9286
    Prev
    Next
    INDEX
    Explanations

    phrases related to power dynamics and political relationships

    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
    1:0.03
    2:0.00
    3:0.15
    4:0.08
    5:0.12
    6:0.04
    7:0.02
    8:0.20
    9:0.18
    10:0.02
    11:0.03
    Negative Logits
     measurement
    -1.69
    fact
    -1.68
    200000
    -1.67
     LINK
    -1.66
    facts
    -1.64
    BuyableInstoreAndOnline
    -1.63
     tid
    -1.56
     digit
    -1.53
     revised
    -1.50
     Haf
    -1.47
    POSITIVE LOGITS
     ordinarily
    1.83
     nowadays
    1.79
     nightmares
    1.75
    resent
    1.75
    audi
    1.72
    pmwiki
    1.72
    oreal
    1.68
     typically
    1.66
    entimes
    1.64
    ��
    1.63
    Activations Density 0.039%

    No Known Activations