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. 6395
    Prev
    Next
    INDEX
    Explanations

    questions and specific actions related to game testing

    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
    0:0.08
    1:0.07
    2:0.05
    3:0.03
    4:0.05
    5:0.29
    6:0.05
    7:0.07
    8:0.04
    9:0.04
    10:0.04
    11:0.12
    Negative Logits
    unts
    -1.97
     gamb
    -1.54
    黒
    -1.54
    uscript
    -1.50
    >>>>>>>>
    -1.49
    ugi
    -1.49
     Preferred
    -1.47
     サーティワン
    -1.47
     Clerk
    -1.47
    Wallet
    -1.43
    POSITIVE LOGITS
    orthy
    1.71
    jri
    1.64
     Ham
    1.63
    hz
    1.60
    phrine
    1.53
     ip
    1.50
    qv
    1.49
    auer
    1.48
     Yar
    1.45
    Hz
    1.44
    Activations Density 0.001%

    No Known Activations