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. 5-ATT-KK
    6. 7574
    Prev
    Next
    INDEX
    Explanations

    instances of the word "salvage" and related phrases indicating recovery of goods or property

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.04
    3:0.06
    4:0.13
    5:0.03
    6:0.03
    7:0.43
    8:0.04
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
    advertisement
    -1.86
    Phys
    -1.83
    gee
    -1.64
    ctors
    -1.62
    Assistant
    -1.61
    comed
    -1.58
    cius
    -1.56
    五
    -1.55
    scient
    -1.55
    phys
    -1.51
    POSITIVE LOGITS
    uctions
    1.72
     salv
    1.70
     wreckage
    1.70
     wounds
    1.67
     losses
    1.62
     wrecked
    1.60
     victories
    1.59
     salvage
    1.56
     derailed
    1.52
     destroyed
    1.51
    Activations Density 0.001%

    No Known Activations