© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 13491
    Prev
    Next
    INDEX
    Explanations

    references to violent actions or conflicts

    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
    1:0.01
    2:0.10
    3:0.07
    4:0.05
    5:0.06
    6:0.02
    7:0.02
    8:0.38
    9:0.11
    10:0.04
    11:0.02
    Negative Logits
    SPONSORED
    -1.71
    verts
    -1.33
    tti
    -1.25
    aring
    -1.17
    ────
    -1.17
    clusive
    -1.16
    VA
    -1.12
    linked
    -1.11
     Hull
    -1.11
     Aden
    -1.10
    POSITIVE LOGITS
    livion
    1.26
    idelines
    1.16
    eanor
    1.09
     unnecessary
    1.08
     professionalism
    1.08
     existence
    1.07
    lyn
    1.05
    pez
    1.05
     Rin
    1.05
     sofa
    1.05
    Activations Density 0.416%

    No Known Activations