© 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 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. 13337
    Prev
    Next
    INDEX
    Explanations

    terms related to admissions, confessions, and acknowledging past mistakes

    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
    0:0.05
    1:0.02
    2:0.08
    3:0.23
    4:0.02
    5:0.17
    6:0.01
    7:0.08
    8:0.02
    9:0.02
    10:0.21
    11:0.01
    Negative Logits
    united
    -2.37
    iscopal
    -2.12
     Recommend
    -2.10
     apparel
    -2.04
     tradem
    -2.03
    compan
    -1.95
    lished
    -1.92
     certific
    -1.92
     stret
    -1.92
     cele
    -1.91
    POSITIVE LOGITS
     mistakes
    3.05
     mistake
    3.05
     errors
    2.44
     wrong
    2.41
     messed
    2.38
     error
    2.37
     faked
    2.32
    errors
    2.31
    mist
    2.22
     folly
    2.21
    Activations Density 0.082%

    No Known Activations