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. 10-ATT-KK
    6. 14613
    Prev
    Next
    INDEX
    Explanations

    quotations and references to expert opinions or statements regarding geopolitical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.32
    2:0.05
    3:0.06
    4:0.03
    5:0.02
    6:0.05
    7:0.09
    8:0.02
    9:0.03
    10:0.10
    11:0.05
    Negative Logits
     provisional
    -3.12
     upside
    -2.77
     rou
    -2.41
     sideways
    -2.38
    leans
    -2.35
    aders
    -2.31
    acements
    -2.24
     BST
    -2.22
     neo
    -2.21
    vis
    -2.21
    POSITIVE LOGITS
     Fire
    7.28
    Fire
    7.25
    fire
    6.79
     fire
    6.50
     FIRE
    5.33
    fires
    5.20
     Fires
    5.17
     blaze
    4.78
     fires
    4.44
     wildfire
    4.30
    Activations Density 0.046%

    No Known Activations