© 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. 19420
    Prev
    Next
    INDEX
    Explanations

    phrases related to the legal system and criminal justice

    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
    0:0.04
    1:0.02
    2:0.13
    3:0.12
    4:0.03
    5:0.40
    6:0.02
    7:0.07
    8:0.04
    9:0.02
    10:0.04
    11:0.01
    Negative Logits
     separation
    -3.19
     burial
    -2.90
     entitle
    -2.86
     protections
    -2.79
     resid
    -2.69
     coffin
    -2.69
     vacancies
    -2.66
     enshr
    -2.64
     limbo
    -2.60
     retirement
    -2.56
    POSITIVE LOGITS
    inous
    3.21
     mastermind
    3.02
    wagen
    2.86
     counterfe
    2.77
     plotting
    2.73
     Guilty
    2.66
    reck
    2.63
     conspiring
    2.60
     sche
    2.52
     Conspiracy
    2.51
    Activations Density 0.270%

    No Known Activations