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. 9-ATT-KK
    6. 7574
    Prev
    Next
    INDEX
    Explanations

    monetary values, especially in financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.08
    2:0.04
    3:0.11
    4:0.03
    5:0.07
    6:0.18
    7:0.07
    8:0.02
    9:0.25
    10:0.03
    11:0.05
    Negative Logits
    Sim
    -3.24
     Donn
    -3.19
     Dino
    -2.97
    EStreamFrame
    -2.85
     Tycoon
    -2.82
     Gim
    -2.77
     Yo
    -2.75
     Pon
    -2.73
     Nikki
    -2.73
     Puppet
    -2.72
    POSITIVE LOGITS
    alde
    3.20
    ██
    3.04
     Albion
    2.82
    alion
    2.79
    alg
    2.76
    dal
    2.73
    ald
    2.70
    Ark
    2.67
     alk
    2.64
    08
    2.56
    Activations Density 0.015%

    No Known Activations