© 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. 14086
    Prev
    Next
    INDEX
    Explanations

    institutions and organizations related to education, conflict, and medical research

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

    mentions of various research and educational institutions

    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
    1:0.04
    2:0.06
    3:0.18
    4:0.01
    5:0.01
    6:0.14
    7:0.12
    8:0.07
    9:0.11
    10:0.05
    11:0.14
    Negative Logits
    ¯
    -1.11
    tty
    -1.10
    mire
    -1.10
    affer
    -1.04
    arily
    -1.00
     outp
    -0.99
    ahime
    -0.98
    ungle
    -0.97
    rily
    -0.96
    oard
    -0.96
    POSITIVE LOGITS
     caut
    1.17
    Active
    1.16
     Robotics
    1.11
     Electrical
    1.08
    Quality
    1.07
     Behavior
    1.07
     Arbit
    1.06
    Technology
    1.06
     Noise
    1.04
     Accountability
    1.04
    Activations Density 0.043%

    No Known Activations