Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18697
    Prev
    Next
    INDEX
    Explanations

    phrases that denote the significance or importance of news stories and reports

    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
    0:0.07
    1:0.03
    2:0.07
    3:0.16
    4:0.06
    5:0.16
    6:0.06
    7:0.06
    8:0.08
    9:0.01
    10:0.15
    11:0.03
    Negative Logits
     amalg
    -2.01
     pse
    -1.93
    ��
    -1.92
     viz
    -1.86
     kindly
    -1.81
     syll
    -1.81
     proofs
    -1.79
     referen
    -1.78
    �
    -1.77
     �
    -1.74
    POSITIVE LOGITS
    Connector
    2.25
     emergencies
    2.19
    agascar
    2.16
     Danger
    2.14
    Emergency
    1.95
     Gamb
    1.90
     Daytona
    1.88
    raz
    1.86
    azard
    1.85
    amphetamine
    1.82
    Activations Density 0.004%

    No Known Activations