© 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. 15260
    Prev
    Next
    INDEX
    Explanations

    statements regarding apologies and accountability in social contexts

    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
    2:0.10
    3:0.22
    4:0.02
    5:0.10
    6:0.01
    7:0.06
    8:0.04
    9:0.01
    10:0.31
    11:0.01
    Negative Logits
    unknown
    -2.29
     unlucky
    -2.28
    fortune
    -2.26
    matched
    -2.18
    owler
    -2.14
    favorite
    -2.07
     misfortune
    -1.94
     vain
    -1.92
    76561
    -1.92
    awed
    -1.90
    POSITIVE LOGITS
     faire
    3.04
    cknow
    2.95
     clearer
    2.91
     rethink
    2.86
     equitable
    2.86
     transparency
    2.85
     responsibly
    2.84
     acknowledging
    2.73
     urgently
    2.71
     honesty
    2.69
    Activations Density 1.270%

    No Known Activations