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. 7-ATT-KK
    6. 9479
    Prev
    Next
    INDEX
    Explanations

    references to sharpness and precision in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.04
    2:0.06
    3:0.07
    4:0.04
    5:0.06
    6:0.04
    7:0.04
    8:0.36
    9:0.05
    10:0.04
    11:0.05
    Negative Logits
    agne
    -1.86
    gery
    -1.74
    ador
    -1.73
     encour
    -1.68
     Costume
    -1.67
    ylum
    -1.66
    clus
    -1.60
     volunt
    -1.59
     Nost
    -1.59
     nonsensical
    -1.59
    POSITIVE LOGITS
    Shar
    2.08
    onday
    2.06
     sharper
    1.93
     razor
    1.88
    sharp
    1.85
     antennas
    1.81
     blades
    1.80
     knives
    1.78
     radar
    1.76
     shar
    1.75
    Activations Density 0.001%

    No Known Activations