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. 5-ATT-KK
    6. 2998
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong emotions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.09
    3:0.04
    4:0.11
    5:0.15
    6:0.25
    7:0.02
    8:0.12
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
     affinity
    -1.45
     corpus
    -1.45
     geography
    -1.43
     jurisdiction
    -1.41
    racuse
    -1.35
     offence
    -1.35
     enrol
    -1.34
    assetsadobe
    -1.33
    displayText
    -1.33
     geographic
    -1.33
    POSITIVE LOGITS
    !!!!
    1.66
     Respect
    1.56
    laughs
    1.56
    !!
    1.50
    Mods
    1.47
    !!!!!
    1.46
     神
    1.45
     Laugh
    1.43
    !!!
    1.42
    Laughs
    1.41
    Activations Density 0.006%

    No Known Activations