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. 18740
    Prev
    Next
    INDEX
    Explanations

    references to academic research and institutions related to stem cell biology and therapies

    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
    0:0.14
    1:0.01
    2:0.36
    3:0.13
    4:0.03
    5:0.07
    6:0.03
    7:0.04
    8:0.07
    9:0.02
    10:0.04
    11:0.02
    Negative Logits
     curfew
    -3.64
     Riders
    -2.92
    panic
    -2.82
    Crime
    -2.79
     shootings
    -2.67
     patriotic
    -2.67
     grievances
    -2.65
     offend
    -2.65
    iesta
    -2.63
     Glock
    -2.62
    POSITIVE LOGITS
     molecular
    5.56
     biochemical
    5.38
     microbial
    5.37
     bacterial
    5.26
     enzymes
    5.24
     microbi
    5.15
     Molecular
    5.10
     biom
    4.95
     tissue
    4.94
     microbes
    4.92
    Activations Density 0.480%

    No Known Activations