© 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. 16330
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to prosecution and court proceedings

    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
    0:0.16
    1:0.12
    2:0.05
    3:0.04
    4:0.05
    5:0.02
    6:0.08
    7:0.12
    8:0.02
    9:0.04
    10:0.20
    11:0.04
    Negative Logits
     Lenn
    -2.93
     Brom
    -2.92
    antage
    -2.89
    overy
    -2.88
    idth
    -2.76
     Bethlehem
    -2.76
    swer
    -2.73
     Aero
    -2.72
     Ain
    -2.64
    Stan
    -2.63
    POSITIVE LOGITS
     mut
    7.38
     Mut
    7.11
    Mut
    6.93
    mut
    6.22
     mutation
    4.56
     mutations
    4.47
     mutated
    4.38
     Mutant
    4.01
     immutable
    3.98
     vec
    3.57
    Activations Density 0.007%

    No Known Activations