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. 10-ATT-KK
    6. 14609
    Prev
    Next
    INDEX
    Explanations

    expressions related to legal or illegal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.03
    2:0.09
    3:0.08
    4:0.06
    5:0.23
    6:0.04
    7:0.07
    8:0.06
    9:0.13
    10:0.07
    11:0.03
    Negative Logits
    †
    -2.48
     Limit
    -2.43
     antim
    -2.31
     MB
    -2.20
    taboola
    -2.18
     derog
    -2.18
    �
    -2.17
     TM
    -2.17
     MA
    -2.10
     ICC
    -2.06
    POSITIVE LOGITS
    Then
    3.42
     awoke
    3.36
    Eventually
    3.33
     hadn
    3.30
     sprang
    3.25
    Suddenly
    3.25
    then
    3.01
     woke
    2.94
    didn
    2.90
    toggle
    2.88
    Activations Density 0.099%

    No Known Activations