© 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. 2-ATT-KK
    11. 15368
    Prev
    Next
    INDEX
    Explanations

    texts discussing controversial or sensitive topics such as surveillance, personal rights, and cultural norms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.03
    2:0.13
    3:0.15
    4:0.03
    5:0.09
    6:0.04
    7:0.07
    8:0.04
    9:0.10
    10:0.14
    11:0.06
    Negative Logits
    abad
    -1.20
    ushima
    -1.17
    装
    -1.14
     pairs
    -1.13
    ittees
    -1.12
    monton
    -1.12
     Rica
    -1.11
    ategor
    -1.09
    arate
    -1.08
    osponsors
    -1.07
    POSITIVE LOGITS
    iest
    1.39
     fallacy
    1.37
     element
    1.34
     portion
    1.31
    liest
    1.30
     dimension
    1.25
     notion
    1.25
     hypothesis
    1.21
     question
    1.20
     aspect
    1.17
    Activations Density 1.178%

    No Known Activations