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. 14566
    Prev
    Next
    INDEX
    Explanations

    connections and relationships in text, particularly conjunctions and phrases that imply continuity or association

    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
    0:0.07
    1:0.08
    2:0.04
    3:0.04
    4:0.07
    5:0.02
    6:0.03
    7:0.43
    8:0.02
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
     Chou
    -3.01
     Wong
    -2.96
     wom
    -2.63
     Mermaid
    -2.62
     Chau
    -2.61
     Welsh
    -2.60
    NG
    -2.56
     NG
    -2.56
     Ong
    -2.55
     Loki
    -2.51
    POSITIVE LOGITS
    idas
    2.65
    atism
    2.60
    itis
    2.59
    046
    2.56
    iations
    2.48
    itaire
    2.40
    viol
    2.37
    hran
    2.35
    iation
    2.35
    146
    2.32
    Activations Density 0.024%

    No Known Activations