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. 9-ATT-KK
    6. 7708
    Prev
    Next
    INDEX
    Explanations

    specific references to legal proceedings and statistics related to criminal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.02
    2:0.04
    3:0.37
    4:0.06
    5:0.06
    6:0.07
    7:0.05
    8:0.04
    9:0.07
    10:0.07
    11:0.03
    Negative Logits
     bananas
    -2.23
     mushrooms
    -2.21
     cocaine
    -2.20
     rye
    -2.12
     tomatoes
    -2.11
     vodka
    -2.06
     pineapple
    -2.04
     virgin
    -2.00
    odka
    -1.99
     gorilla
    -1.97
    POSITIVE LOGITS
     Examiner
    2.63
     Editorial
    2.55
     Spotlight
    2.44
     editors
    2.40
     Advisory
    2.33
     Review
    2.32
     editorial
    2.31
     Inquiry
    2.29
     Editors
    2.28
     Insight
    2.26
    Activations Density 0.524%

    No Known Activations