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. 10609
    Prev
    Next
    INDEX
    Explanations

    evidence and references to legal decisions and court cases

    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
    2:0.08
    3:0.04
    4:0.05
    5:0.03
    6:0.37
    7:0.04
    8:0.05
    9:0.15
    10:0.02
    11:0.03
    Negative Logits
    istor
    -4.14
     LCD
    -3.83
    igi
    -3.75
     Ichigo
    -3.67
    Interstitial
    -3.60
    Shield
    -3.47
    glomer
    -3.34
    Cu
    -3.28
    assium
    -3.27
    �士
    -3.22
    POSITIVE LOGITS
    Wild
    9.88
     Wild
    9.59
    wild
    8.72
     wild
    7.21
     Wildlife
    6.43
     Wilderness
    6.21
     Wolves
    5.95
     wildlife
    5.80
     wildfire
    5.61
     wilderness
    5.55
    Activations Density 0.020%

    No Known Activations