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. 44408
    Prev
    Next
    INDEX
    Explanations

    phrases related to executions and violent punishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.02
    2:0.09
    3:0.06
    4:0.06
    5:0.07
    6:0.06
    7:0.08
    8:0.03
    9:0.06
    10:0.31
    11:0.08
    Negative Logits
     Agric
    -2.05
    channelAvailability
    -1.90
     Rail
    -1.87
     GOODMAN
    -1.72
     Lobby
    -1.71
     Indust
    -1.68
    depend
    -1.66
     Cooperative
    -1.62
    osponsors
    -1.60
     Investments
    -1.58
    POSITIVE LOGITS
    redd
    1.80
     hoax
    1.79
     spree
    1.58
    zynski
    1.57
     shaved
    1.56
     unidentified
    1.55
    rator
    1.54
     faked
    1.54
     killings
    1.52
    Buzz
    1.48
    Activations Density 0.001%

    No Known Activations