© 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. 12376
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal regulations and authorities

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

    phrases that express alignment or consistency with values, laws, or principles

    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
    0:0.01
    1:0.02
    2:0.07
    3:0.19
    4:0.01
    5:0.02
    6:0.04
    7:0.09
    8:0.09
    9:0.21
    10:0.07
    11:0.12
    Negative Logits
    roy
    -1.40
    bub
    -1.29
    igs
    -1.23
    ener
    -1.22
    anamo
    -1.21
     danced
    -1.19
    URE
    -1.17
    ess
    -1.16
    bots
    -1.15
    otom
    -1.15
    POSITIVE LOGITS
    contin
    1.32
     causation
    1.31
     continuity
    1.31
     chronological
    1.30
     continuous
    1.24
     continuation
    1.24
     kosher
    1.19
     referral
    1.19
     qualitative
    1.18
     survival
    1.17
    Activations Density 0.004%

    No Known Activations