Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11372
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize safety and security in various contexts

    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
    0:0.06
    1:0.02
    2:0.10
    3:0.29
    4:0.02
    5:0.11
    6:0.02
    7:0.05
    8:0.03
    9:0.03
    10:0.20
    11:0.02
    Negative Logits
     resentment
    -2.11
     historian
    -2.10
    govtrack
    -2.07
     inspector
    -2.02
     distortions
    -2.01
     Inspector
    -1.99
    azeera
    -1.95
     genius
    -1.94
    detail
    -1.94
     Monstrous
    -1.93
    POSITIVE LOGITS
     indoors
    2.17
     beverages
    2.14
     outdoors
    2.06
    ********************************
    2.05
     cannabis
    2.01
     safe
    2.00
    enter
    2.00
     beverage
    2.00
     safest
    1.95
    noon
    1.92
    Activations Density 0.030%

    No Known Activations