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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 182
    Prev
    Next
    INDEX
    Explanations

    dates and numerical references related to events and publications

    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
    0:0.05
    1:0.02
    2:0.03
    3:0.26
    4:0.03
    5:0.15
    6:0.03
    7:0.07
    8:0.07
    9:0.03
    10:0.15
    11:0.06
    Negative Logits
     congr
    -2.27
     Guth
    -2.06
     forgiveness
    -1.99
     empathy
    -1.98
     PubMed
    -1.97
     gratitude
    -1.93
     thank
    -1.92
    iversary
    -1.90
    ��
    -1.86
     Verify
    -1.86
    POSITIVE LOGITS
    IDE
    2.52
    NAS
    2.31
    WASHINGTON
    2.28
    OD
    2.02
    ENG
    1.99
    pak
    1.89
    FORE
    1.88
    ASHINGTON
    1.86
    ORTS
    1.84
    ATIONAL
    1.82
    Activations Density 0.017%

    No Known Activations