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. 8386
    Prev
    Next
    INDEX
    Explanations

    numerical values and related statistical information

    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
    0:0.03
    1:0.04
    2:0.22
    3:0.06
    4:0.03
    5:0.05
    6:0.05
    7:0.08
    8:0.14
    9:0.05
    10:0.13
    11:0.06
    Negative Logits
    icc
    -0.94
    heid
    -0.88
     VIEW
    -0.88
    abet
    -0.88
    redd
    -0.87
    NESS
    -0.85
    milo
    -0.83
    icons
    -0.81
    acea
    -0.81
    organisms
    -0.81
    POSITIVE LOGITS
     respectively
    1.47
     Dragonbound
    1.00
    ilogy
    0.92
     Dynam
    0.91
     Schr
    0.90
     Simulator
    0.90
     Slightly
    0.89
    ruary
    0.88
     Bastard
    0.87
     equivalent
    0.86
    Activations Density 0.174%

    No Known Activations