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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21512
    Prev
    Next
    INDEX
    Explanations

    articles and conjunctions that indicate conditions or expectations

    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
    0:0.07
    1:0.06
    2:0.04
    3:0.05
    4:0.22
    5:0.05
    6:0.08
    7:0.13
    8:0.03
    9:0.06
    10:0.05
    11:0.10
    Negative Logits
    ayne
    -2.27
    amation
    -2.19
    ricane
    -2.16
     hurts
    -2.09
     Lauder
    -2.08
    alian
    -2.06
    english
    -2.06
    ogun
    -2.06
     Samoa
    -2.05
    ^^
    -2.04
    POSITIVE LOGITS
     curiosity
    4.44
     Curious
    3.28
     discovery
    3.11
     curious
    3.01
     intrigued
    2.92
     Curiosity
    2.89
     inqu
    2.83
     puzz
    2.76
     experimentation
    2.71
     hypothes
    2.71
    Activations Density 0.001%

    No Known Activations