© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19009
    Prev
    Next
    INDEX
    Explanations

    legal terms related to guilty pleas and court cases

    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
    0:0.06
    1:0.02
    2:0.07
    3:0.10
    4:0.03
    5:0.07
    6:0.03
    7:0.12
    8:0.04
    9:0.02
    10:0.38
    11:0.01
    Negative Logits
    yip
    -2.10
    rified
    -1.96
    roud
    -1.94
     remind
    -1.93
    ichever
    -1.93
     silhou
    -1.90
     momentum
    -1.89
     bothered
    -1.86
    ansky
    -1.85
    itant
    -1.82
    POSITIVE LOGITS
     apologized
    2.02
     redeem
    1.91
    emn
    1.90
     pleaded
    1.88
    Judge
    1.85
    sett
    1.84
    ailable
    1.84
     forgiven
    1.82
    istrates
    1.82
     confess
    1.81
    Activations Density 0.038%

    No Known Activations