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. 9386
    Prev
    Next
    INDEX
    Explanations

    words related to laws, enforcement, and proper roles in various contexts

    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
    0:0.37
    1:0.04
    2:0.01
    3:0.12
    4:0.09
    5:0.09
    6:0.04
    7:0.02
    8:0.09
    9:0.05
    10:0.02
    11:0.02
    Negative Logits
     unanimous
    -1.43
    theless
    -1.43
    izabeth
    -1.42
    laugh
    -1.38
     Crosby
    -1.38
     Ic
    -1.37
     fame
    -1.34
     surprising
    -1.32
     Lilly
    -1.31
     whom
    -1.30
    POSITIVE LOGITS
    iquette
    1.73
     procedures
    1.71
    Management
    1.69
    �
    1.65
     etiquette
    1.62
     vetting
    1.60
    ogy
    1.60
     stewards
    1.59
     evaluation
    1.58
    urgy
    1.55
    Activations Density 0.005%

    No Known Activations