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. 3-ATT-KK
    6. 10566
    Prev
    Next
    INDEX
    Explanations

    key terms related to business and industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.05
    2:0.07
    3:0.08
    4:0.03
    5:0.05
    6:0.08
    7:0.27
    8:0.05
    9:0.04
    10:0.07
    11:0.14
    Negative Logits
    ��
    -1.58
    =-=-=-=-
    -1.52
    ��
    -1.48
     Flavoring
    -1.46
    ONSORED
    -1.39
    ETF
    -1.38
    anton
    -1.35
     Lumpur
    -1.29
    )",
    -1.27
     millenn
    -1.27
    POSITIVE LOGITS
     spoiler
    1.40
    ranch
    1.36
     oats
    1.20
     behold
    1.15
     spreads
    1.10
     decomp
    1.10
    medium
    1.08
    ocon
    1.06
     Omaha
    1.04
    �
    1.04
    Activations Density 0.386%

    No Known Activations