© 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. 3-ATT-KK
    11. 12421
    Prev
    Next
    INDEX
    Explanations

    statements made by individuals during court proceedings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words related to law and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.08
    2:0.07
    3:0.06
    4:0.11
    5:0.06
    6:0.08
    7:0.09
    8:0.07
    9:0.07
    10:0.06
    11:0.06
    Negative Logits
     respectively
    -1.29
    seless
    -1.20
     geographically
    -1.18
    ailable
    -1.17
     optimized
    -1.16
     globally
    -1.14
    oppable
    -1.11
     customizable
    -1.09
     standalone
    -1.08
     collectively
    -1.07
    POSITIVE LOGITS
    lio
    1.35
    ZE
    1.30
    ena
    1.25
    INA
    1.24
    zinski
    1.24
    anke
    1.24
    Dialogue
    1.23
    rate
    1.23
     POW
    1.21
    REP
    1.20
    Activations Density 0.008%

    No Known Activations