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. 14651
    Prev
    Next
    INDEX
    Explanations

    connections related to messaging apps and communication platforms

    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
    0:0.04
    1:0.03
    2:0.04
    3:0.05
    4:0.08
    5:0.03
    6:0.05
    7:0.37
    8:0.02
    9:0.04
    10:0.05
    11:0.13
    Negative Logits
    chat
    -2.95
     prayer
    -2.66
     chants
    -2.56
     Spectre
    -2.50
    Chat
    -2.48
     chanted
    -2.46
     Telegram
    -2.45
     Chat
    -2.42
     Medina
    -2.32
     Skype
    -2.31
    POSITIVE LOGITS
     EF
    2.78
    EF
    2.69
    Fu
    2.65
     Eco
    2.63
     Blanc
    2.53
     predec
    2.45
    Drag
    2.32
    ylene
    2.32
     EC
    2.26
     Democr
    2.25
    Activations Density 0.008%

    No Known Activations