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. 9307
    Prev
    Next
    INDEX
    Explanations

    references to flying and aviation-related activities

    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
    0:0.15
    1:0.03
    2:0.01
    3:0.13
    4:0.03
    5:0.11
    6:0.03
    7:0.02
    8:0.35
    9:0.07
    10:0.01
    11:0.01
    Negative Logits
    roma
    -1.80
    gem
    -1.66
    algia
    -1.66
     Pwr
    -1.60
     weakness
    -1.60
    viation
    -1.60
    uilding
    -1.54
    archives
    -1.53
    abase
    -1.53
    letal
    -1.50
    POSITIVE LOGITS
     airplanes
    1.98
     sails
    1.91
     flights
    1.85
     sail
    1.83
     flying
    1.82
     tours
    1.81
     flown
    1.80
     jets
    1.79
     cruise
    1.78
     helicopters
    1.78
    Activations Density 0.021%

    No Known Activations