© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15209
    Prev
    Next
    INDEX
    Explanations

    phrases indicating various locations or directives in a context

    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
    0:0.04
    1:0.03
    2:0.03
    3:0.14
    4:0.08
    5:0.02
    6:0.04
    7:0.36
    8:0.02
    9:0.02
    10:0.04
    11:0.11
    Negative Logits
     Scand
    -3.18
     Utah
    -2.99
    Salt
    -2.96
    Utah
    -2.85
     Vive
    -2.77
     Vir
    -2.75
     Santana
    -2.72
     Sal
    -2.64
     Lat
    -2.53
    Roy
    -2.50
    POSITIVE LOGITS
    azeera
    2.58
    imaru
    2.50
     EDT
    2.46
    omers
    2.44
    ゴン
    2.33
    pload
    2.29
     lantern
    2.28
    ahime
    2.27
     Bowen
    2.25
    ibilities
    2.24
    Activations Density 0.002%

    No Known Activations