© 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. 14039
    Prev
    Next
    INDEX
    Explanations

    arguments for and against journaling, particularly focusing on personal feelings and experiences

    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
    0:0.09
    1:0.05
    2:0.10
    3:0.10
    4:0.03
    5:0.02
    6:0.16
    7:0.16
    8:0.02
    9:0.02
    10:0.11
    11:0.08
    Negative Logits
     Hezbollah
    -2.44
     Bravo
    -2.44
     McAuliffe
    -2.39
     disco
    -2.38
    arrell
    -2.36
     Cater
    -2.31
     Castro
    -2.29
    poke
    -2.15
     Beir
    -2.15
     Pence
    -2.15
    POSITIVE LOGITS
     journal
    5.44
     Journals
    4.97
     Journal
    4.79
     journals
    4.60
    Journal
    4.45
    journal
    4.32
     Editors
    3.31
    ournal
    3.07
     Quarterly
    3.03
     Gazette
    3.01
    Activations Density 0.014%

    No Known Activations