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. 20702
    Prev
    Next
    INDEX
    Explanations

    text that conveys strong emotional or sensational elements

    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
    1:0.04
    2:0.03
    3:0.04
    4:0.09
    5:0.08
    6:0.04
    7:0.05
    8:0.13
    9:0.03
    10:0.04
    11:0.35
    Negative Logits
     mah
    -2.80
     prin
    -2.76
     favor
    -2.67
     subur
    -2.65
     coh
    -2.65
     eleph
    -2.61
     favorites
    -2.55
     mustache
    -2.50
     vigilance
    -2.49
     wellness
    -2.48
    POSITIVE LOGITS
    SPONSORED
    4.48
    Image
    3.81
    BBC
    3.73
    Video
    3.47
    cript
    3.39
    (
    3.33
    Read
    3.30
    (-
    3.22
    poll
    3.09
    Manchester
    3.01
    Activations Density 0.004%

    No Known Activations