© 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. 3-ATT-KK
    11. 8256
    Prev
    Next
    INDEX
    Explanations

    references to constitutional rights and related legal concepts

    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
    0:0.02
    1:0.10
    2:0.08
    3:0.03
    4:0.03
    5:0.04
    6:0.07
    7:0.06
    8:0.18
    9:0.07
    10:0.07
    11:0.20
    Negative Logits
    Pie
    -1.25
     pops
    -1.20
     trimmed
    -1.17
     anew
    -1.17
     finally
    -1.16
     srfAttach
    -1.15
    Pink
    -1.14
     tidy
    -1.13
    morrow
    -1.11
     soothing
    -1.11
    POSITIVE LOGITS
    lihood
    1.38
     precedent
    1.25
     Motion
    1.19
    ccess
    1.17
    yrights
    1.16
     Proposition
    1.13
     doctrine
    1.12
     libel
    1.10
    ague
    1.09
     angle
    1.08
    Activations Density 0.025%

    No Known Activations