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. 83
    Prev
    Next
    INDEX
    Explanations

    references to specific companies and their products or practices within the context of technology and market trends

    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
    0:0.12
    1:0.03
    2:0.32
    3:0.12
    4:0.03
    5:0.05
    6:0.03
    7:0.05
    8:0.04
    9:0.03
    10:0.10
    11:0.04
    Negative Logits
     emergency
    -3.31
    Emergency
    -2.98
     inconvenience
    -2.97
     emergencies
    -2.94
     damages
    -2.89
     distress
    -2.86
     misery
    -2.79
     severity
    -2.75
     jeopardy
    -2.69
     inconven
    -2.67
    POSITIVE LOGITS
     pract
    3.63
     pioneered
    3.59
     practiced
    3.40
     reused
    3.33
     style
    3.31
    Traditional
    3.28
     traditions
    3.23
     styles
    3.22
     tradition
    3.22
    inspired
    3.21
    Activations Density 0.302%

    No Known Activations