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. 14742
    Prev
    Next
    INDEX
    Explanations

    references to intelligence and legal cases related to criminal activities or laws

    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
    0:0.03
    1:0.03
    2:0.03
    3:0.05
    4:0.08
    5:0.02
    6:0.16
    7:0.31
    8:0.01
    9:0.03
    10:0.02
    11:0.18
    Negative Logits
     Pets
    -2.37
     Vote
    -2.29
     Movies
    -2.15
    dogs
    -2.10
     Vend
    -2.09
    DIT
    -2.07
    bet
    -2.05
     Dogs
    -2.03
     Visit
    -2.01
     Particip
    -1.96
    POSITIVE LOGITS
     cases
    2.79
     case
    2.65
     Horus
    2.52
     Kemp
    2.48
     Sturgeon
    2.43
     Turner
    2.42
     Yose
    2.40
     ILCS
    2.36
    emp
    2.35
    stadt
    2.35
    Activations Density 0.061%

    No Known Activations