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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8520
    Prev
    Next
    INDEX
    Explanations

    quantitative figures and statistics related to people and institutions

    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
    1:0.07
    2:0.14
    3:0.04
    4:0.02
    5:0.05
    6:0.08
    7:0.08
    8:0.14
    9:0.07
    10:0.09
    11:0.13
    Negative Logits
     Retro
    -0.94
    advant
    -0.91
     trademark
    -0.90
     retrospective
    -0.87
    alogy
    -0.87
     envy
    -0.86
    ��
    -0.84
     doub
    -0.83
     Libre
    -0.83
     patent
    -0.83
    POSITIVE LOGITS
    yip
    1.12
    yz
    1.05
    iates
    1.03
    ember
    0.98
    merce
    0.97
    ewitness
    0.96
    depending
    0.92
    sburg
    0.92
    20439
    0.91
    adish
    0.91
    Activations Density 0.015%

    No Known Activations