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. 11307
    Prev
    Next
    INDEX
    Explanations

    instances of legal proceedings and the justice system's response to criminal behavior

    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
    1:0.04
    2:0.11
    3:0.15
    4:0.06
    5:0.10
    6:0.03
    7:0.10
    8:0.17
    9:0.03
    10:0.04
    11:0.06
    Negative Logits
    Americans
    -3.04
    luster
    -3.03
     Democr
    -3.00
     centers
    -2.96
     globalization
    -2.96
    NPR
    -2.95
    imize
    -2.92
     civilizations
    -2.90
    avored
    -2.90
    NYSE
    -2.90
    POSITIVE LOGITS
     apologised
    5.03
     offences
    4.94
     counselling
    4.87
     recognised
    4.83
     paed
    4.81
     £
    4.81
     apologise
    4.58
     NSW
    4.46
     realised
    4.42
     Adelaide
    4.40
    Activations Density 0.648%

    No Known Activations