© 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. 10-ATT-KK
    11. 12523
    Prev
    Next
    INDEX
    Explanations

    phrases related to corruption and financial misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.10
    2:0.35
    3:0.05
    4:0.06
    5:0.05
    6:0.05
    7:0.05
    8:0.04
    9:0.05
    10:0.04
    11:0.06
    Negative Logits
     metab
    -2.99
     til
    -2.94
     Neh
    -2.72
     dra
    -2.69
     schizophren
    -2.65
     typ
    -2.64
     GE
    -2.63
     PET
    -2.57
     augmented
    -2.55
     anat
    -2.55
    POSITIVE LOGITS
    000
    5.59
     000
    5.09
    0002
    4.90
     00
    4.76
    0010
    4.51
    001
    4.31
    0000
    4.20
    0001
    4.19
     0004
    4.18
     Hundred
    4.14
    Activations Density 0.004%

    No Known Activations