© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14272
    Prev
    Next
    INDEX
    Explanations

    references to locations and geographical entities in Mississippi

    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
    0:0.31
    1:0.05
    2:0.04
    3:0.04
    4:0.05
    5:0.02
    6:0.08
    7:0.12
    8:0.02
    9:0.05
    10:0.14
    11:0.03
    Negative Logits
     UID
    -3.64
     Argentine
    -3.58
     Argent
    -3.54
     Kur
    -3.48
     Zot
    -3.41
     Buenos
    -3.26
     Container
    -3.18
     espresso
    -3.17
     Czech
    -3.17
     Clockwork
    -3.12
    POSITIVE LOGITS
     Mississippi
    7.93
     Hatt
    6.18
    Jackson
    5.82
     Jackson
    5.81
     Mississ
    5.38
     Bulldogs
    4.54
     Shelby
    4.36
    ippi
    4.36
     LSU
    4.29
    Alabama
    4.21
    Activations Density 0.018%

    No Known Activations