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. 3-ATT-KK
    6. 8340
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs that express strong emotions or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.03
    2:0.20
    3:0.03
    4:0.01
    5:0.02
    6:0.04
    7:0.10
    8:0.20
    9:0.19
    10:0.06
    11:0.03
    Negative Logits
     cube
    -1.11
     stockpile
    -1.05
    pez
    -1.04
     organise
    -1.04
    onductor
    -1.02
    }{
    -1.02
     distinction
    -1.01
     phyl
    -1.01
     commute
    -0.98
     township
    -0.98
    POSITIVE LOGITS
    soDeliveryDate
    1.69
     Roose
    1.35
    cean
    1.29
     Miko
    1.27
    nikov
    1.22
    jee
    1.18
    quickShipAvailable
    1.18
     kidding
    1.17
    stories
    1.17
    acly
    1.16
    Activations Density 0.012%

    No Known Activations