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. 9538
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to governmental policies and military involvement

    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
    0:0.48
    1:0.03
    2:0.03
    3:0.06
    4:0.06
    5:0.05
    6:0.05
    7:0.02
    8:0.07
    9:0.06
    10:0.02
    11:0.02
    Negative Logits
     Swordsman
    -1.93
     Processor
    -1.81
     wisely
    -1.77
     bartender
    -1.76
     Crate
    -1.75
     Tycoon
    -1.74
     Sorceress
    -1.69
     towed
    -1.69
    epad
    -1.68
     Calculator
    -1.66
    POSITIVE LOGITS
    izations
    2.60
    earances
    2.48
    ocations
    2.37
    uations
    2.34
    alties
    2.33
    usions
    2.33
     interventions
    2.32
     commitments
    2.26
     judgments
    2.24
    earance
    2.23
    Activations Density 0.816%

    No Known Activations