© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10535
    Prev
    Next
    INDEX
    Explanations

    instances of legal and regulatory processes or events

    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
    0:0.03
    1:0.01
    2:0.06
    3:0.29
    4:0.02
    5:0.05
    6:0.01
    7:0.06
    8:0.02
    9:0.01
    10:0.35
    11:0.02
    Negative Logits
     tomorrow
    -2.92
     nowadays
    -2.68
     hereafter
    -2.64
     anytime
    -2.43
     future
    -2.31
     someday
    -2.30
     continuum
    -2.27
     depends
    -2.17
     anymore
    -2.15
    next
    -2.08
    POSITIVE LOGITS
    failed
    3.24
     failed
    3.19
     complained
    2.94
     refused
    2.93
     unsuccessful
    2.91
     botched
    2.74
    ewitness
    2.73
     unsuccessfully
    2.70
     breached
    2.67
     protested
    2.62
    Activations Density 0.308%

    No Known Activations