© 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. 3-ATT-KK
    11. 10631
    Prev
    Next
    INDEX
    Explanations

    expressions related to creation or imagination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    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
    2:0.09
    3:0.19
    4:0.03
    5:0.03
    6:0.07
    7:0.06
    8:0.05
    9:0.19
    10:0.07
    11:0.10
    Negative Logits
    anwhile
    -1.57
     incentiv
    -1.47
    ailability
    -1.41
     discretion
    -1.27
    seek
    -1.25
     turnover
    -1.18
    commit
    -1.17
    leneck
    -1.15
    ocre
    -1.15
     spons
    -1.15
    POSITIVE LOGITS
     Mata
    1.39
    �
    1.38
     FANTASY
    1.38
     Ghosts
    1.36
     QUEST
    1.22
     Flames
    1.20
     Yates
    1.20
     Poc
    1.17
     Zi
    1.16
     IL
    1.15
    Activations Density 0.001%

    No Known Activations