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. 9-ATT-KK
    6. 7609
    Prev
    Next
    INDEX
    Explanations

    patterns indicating dates and numerical information in contexts related to events or timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.37
    2:0.02
    3:0.05
    4:0.05
    5:0.05
    6:0.07
    7:0.04
    8:0.03
    9:0.10
    10:0.04
    11:0.09
    Negative Logits
     abusers
    -2.86
    lio
    -2.63
     Nightmare
    -2.62
    atorial
    -2.49
    Numbers
    -2.48
     Playoff
    -2.46
     Healer
    -2.42
    aze
    -2.41
    "]=>
    -2.36
    laim
    -2.35
    POSITIVE LOGITS
    03
    5.13
     05
    4.91
     03
    4.91
    04
    4.88
    05
    4.81
     04
    4.73
     02
    4.69
     07
    4.57
     06
    4.53
    02
    4.39
    Activations Density 0.007%

    No Known Activations