© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 14205
    Prev
    Next
    INDEX
    Explanations

    words related to rules or restrictions

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

    prepositions and articles, indicating discussions about rules or regulations

    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
    3:0.22
    4:0.02
    5:0.03
    6:0.05
    7:0.18
    8:0.06
    9:0.10
    10:0.08
    11:0.11
    Negative Logits
     Schwar
    -1.10
    dL
    -1.06
    ravis
    -1.04
    ptroller
    -1.01
     Jill
    -1.01
    Jet
    -0.99
    rites
    -0.98
     pulp
    -0.97
    FN
    -0.97
    sonian
    -0.96
    POSITIVE LOGITS
    taboola
    1.35
    erous
    1.34
    ���
    1.25
    ascript
    1.23
    catentry
    1.22
     clauses
    1.20
     restricts
    1.18
     thresholds
    1.15
    anchester
    1.09
    eatures
    1.08
    Activations Density 0.016%

    No Known Activations