© 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. 9-ATT-KK
    11. 2249
    Prev
    Next
    INDEX
    Explanations

    elements related to cleanliness and maintenance

    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
    0:0.10
    1:0.01
    2:0.41
    3:0.11
    4:0.03
    5:0.09
    6:0.05
    7:0.05
    8:0.04
    9:0.03
    10:0.03
    11:0.01
    Negative Logits
     Mov
    -2.76
    PsyNetMessage
    -2.64
    ajor
    -2.51
     hostage
    -2.47
    anguard
    -2.46
     Kou
    -2.45
    voice
    -2.44
     Rebellion
    -2.42
     SAS
    -2.41
    Supported
    -2.37
    POSITIVE LOGITS
     cleaning
    6.41
     disinfect
    5.89
     cleaned
    5.76
     clean
    5.50
     hygiene
    5.47
     cleaners
    5.38
     cleans
    5.29
     scrub
    5.27
     cleanup
    5.25
     cleansing
    5.14
    Activations Density 0.857%

    No Known Activations