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. 14564
    Prev
    Next
    INDEX
    Explanations

    names and titles related to law enforcement or judicial proceedings

    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
    3:0.04
    4:0.05
    5:0.27
    6:0.03
    7:0.05
    8:0.02
    9:0.29
    10:0.03
    11:0.08
    Negative Logits
    Topics
    -2.56
     merits
    -2.37
     continue
    -2.37
    athered
    -2.29
    Posted
    -2.24
    qt
    -2.21
    Tags
    -2.20
     continues
    -2.20
     progress
    -2.12
    continue
    -2.11
    POSITIVE LOGITS
    ゴン
    2.75
     informing
    2.66
    ieving
    2.60
    perty
    2.53
     apologizing
    2.50
     abruptly
    2.42
     Immediately
    2.40
    pecting
    2.40
     frantically
    2.38
    quickShipAvailable
    2.38
    Activations Density 0.013%

    No Known Activations