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. 1-ATT-KK
    6. 6357
    Prev
    Next
    INDEX
    Explanations

    phrases related to military operations and investigations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    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
    1:0.08
    2:0.05
    3:0.01
    4:0.07
    5:0.05
    6:0.07
    7:0.06
    8:0.04
    9:0.03
    10:0.03
    11:0.10
    Negative Logits
    folk
    -1.90
    borg
    -1.74
    cience
    -1.66
    olson
    -1.62
    ample
    -1.57
    nikov
    -1.56
    heit
    -1.55
    ilty
    -1.54
    chy
    -1.52
    oxide
    -1.51
    POSITIVE LOGITS
    ENTION
    1.75
     Gates
    1.65
     Documentation
    1.55
     Barrier
    1.54
    Current
    1.46
     Invisible
    1.43
     Azerb
    1.41
    Wiki
    1.41
     Hels
    1.39
    ダ
    1.37
    Activations Density 0.006%

    No Known Activations