© 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. 14235
    Prev
    Next
    INDEX
    Explanations

    references to legal actions and penalties

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

    references to quantities or numerical values

    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
    1:0.01
    2:0.18
    3:0.26
    4:0.01
    5:0.01
    6:0.13
    7:0.05
    8:0.03
    9:0.09
    10:0.05
    11:0.10
    Negative Logits
    eri
    -1.28
    Prince
    -1.24
    agree
    -1.15
    primary
    -1.13
    Charl
    -1.12
    hare
    -1.11
    ��
    -1.10
     Plum
    -1.09
     Sapphire
    -1.07
    verson
    -1.07
    POSITIVE LOGITS
     ultras
    1.25
    icter
    1.24
    cedented
    1.24
    istant
    1.22
    haus
    1.20
     Instruct
    1.19
    dfx
    1.18
     Inquis
    1.15
     overhe
    1.14
    perty
    1.14
    Activations Density 0.042%

    No Known Activations