© 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. 9-ATT-KK
    11. 10905
    Prev
    Next
    INDEX
    Explanations

    references to the magazine "LIFE" and its various issues or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    2:0.07
    3:0.15
    4:0.05
    5:0.12
    6:0.09
    7:0.06
    8:0.04
    9:0.07
    10:0.03
    11:0.12
    Negative Logits
     Alz
    -2.52
     Sed
    -2.38
     Sent
    -2.33
     apes
    -2.31
     Tex
    -2.30
     deserts
    -2.27
     Tik
    -2.25
     Pens
    -2.21
     Tau
    -2.18
     Tah
    -2.16
    POSITIVE LOGITS
     PR
    3.16
     INFO
    3.07
    PR
    2.92
    PRO
    2.84
    LAB
    2.84
     DEBUG
    2.77
    LOCK
    2.77
    FOX
    2.67
    PL
    2.63
    LOG
    2.56
    Activations Density 0.001%

    No Known Activations