© 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. 15476
    Prev
    Next
    INDEX
    Explanations

    names of individuals and references to groups or entities involved in events or actions

    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
    0:0.02
    1:0.02
    2:0.03
    3:0.04
    4:0.04
    5:0.26
    6:0.03
    7:0.06
    8:0.03
    9:0.31
    10:0.02
    11:0.08
    Negative Logits
     Until
    -2.59
    til
    -2.46
    until
    -2.39
    Until
    -2.35
    ウス
    -2.24
     may
    -2.20
     Cure
    -2.12
     Became
    -2.09
     Survive
    -2.02
     Gutenberg
    -1.96
    POSITIVE LOGITS
     apologizing
    2.98
     congrat
    2.90
     pleading
    2.65
     thanking
    2.64
     requesting
    2.63
     inqu
    2.62
     asking
    2.55
     informing
    2.51
     packing
    2.51
     blasting
    2.50
    Activations Density 0.070%

    No Known Activations