© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12725
    Prev
    Next
    INDEX
    Explanations

    numbers and financial information

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

    quantitative data and statistics related to employment and economic metrics

    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
    0:0.06
    1:0.05
    2:0.05
    3:0.03
    4:0.31
    5:0.11
    6:0.06
    7:0.04
    8:0.03
    9:0.04
    10:0.12
    11:0.04
    Negative Logits
    thora
    -1.70
    etheless
    -1.66
    fml
    -1.66
    shapeshifter
    -1.63
    abase
    -1.62
    assed
    -1.61
    reply
    -1.59
    ��
    -1.57
    acht
    -1.57
    appro
    -1.55
    POSITIVE LOGITS
     Deliver
    1.97
     Plain
    1.82
     Sabb
    1.75
     ®
    1.73
    )--
    1.67
     Prov
    1.67
     Achieve
    1.64
     Hedge
    1.56
     Silk
    1.55
    rained
    1.54
    Activations Density 0.104%

    No Known Activations