© 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. 24211
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to washing and cleaning

    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
    0:0.07
    1:0.03
    2:0.07
    3:0.17
    4:0.03
    5:0.08
    6:0.03
    7:0.06
    8:0.03
    9:0.02
    10:0.31
    11:0.05
    Negative Logits
    ◼
    -2.11
    ITNESS
    -1.85
    nostic
    -1.76
     Commando
    -1.76
     hostage
    -1.74
     SEE
    -1.73
     Robertson
    -1.72
     blackmail
    -1.69
    tera
    -1.68
     depends
    -1.67
    POSITIVE LOGITS
     thoroughly
    2.77
    aundering
    2.35
     anew
    2.32
     clean
    2.32
     manually
    2.31
     carefully
    2.31
     cleaned
    2.24
     properly
    2.21
     Remove
    2.20
     meticulously
    2.18
    Activations Density 0.063%

    No Known Activations