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. 8523
    Prev
    Next
    INDEX
    Explanations

    terms related to radiation and its effects on health

    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
    0:0.04
    1:0.04
    2:0.18
    3:0.06
    4:0.03
    5:0.04
    6:0.09
    7:0.10
    8:0.12
    9:0.06
    10:0.08
    11:0.11
    Negative Logits
     Means
    -1.10
    田
    -1.07
    �
    -0.94
     Altern
    -0.93
     Onion
    -0.93
     Lets
    -0.93
    ÃÂ
    -0.93
     Izan
    -0.92
     ende
    -0.91
     Cyn
    -0.87
    POSITIVE LOGITS
    ouls
    1.21
     belonging
    1.12
    older
    1.05
    ufficient
    1.00
     interact
    0.98
     interacted
    0.94
    fml
    0.92
    osity
    0.92
    arantine
    0.91
     etc
    0.91
    Activations Density 0.277%

    No Known Activations