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. 6274
    Prev
    Next
    INDEX
    Explanations

    coding syntax related phrases and email addresses

    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
    0:0.06
    1:0.09
    2:0.15
    3:0.09
    4:0.11
    5:0.04
    6:0.04
    7:0.09
    8:0.05
    9:0.06
    10:0.11
    11:0.06
    Negative Logits
    lyak
    -1.01
     behavi
    -0.99
     disadvant
    -0.96
     citiz
    -0.95
    xus
    -0.94
    leck
    -0.94
    ioned
    -0.93
     conclud
    -0.92
    conservancy
    -0.91
     challeng
    -0.90
    POSITIVE LOGITS
    _
    1.06
    0
    0.93
    ^
    0.92
     |
    0.91
    404
    0.89
     ||
    0.89
    mc
    0.89
     html
    0.86
    Print
    0.86
    cf
    0.86
    Activations Density 0.246%

    No Known Activations