© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 21450
    Prev
    Next
    INDEX
    Explanations

    terms related to various forms of violent actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.07
    1:0.03
    2:0.40
    3:0.07
    4:0.09
    5:0.07
    6:0.02
    7:0.02
    8:0.05
    9:0.05
    10:0.05
    11:0.03
    Negative Logits
    ioxide
    -1.76
     Cosponsors
    -1.45
    ��
    -1.41
    taboola
    -1.41
     guiActiveUnfocused
    -1.38
     Sorce
    -1.35
    Spons
    -1.27
    irie
    -1.25
     Rican
    -1.23
    ーテ
    -1.18
    POSITIVE LOGITS
     pains
    1.29
    wed
    1.24
     deer
    1.19
     sorts
    1.14
    inki
    1.14
     calves
    1.13
    igans
    1.13
    angs
    1.12
     tune
    1.12
    assetsadobe
    1.07
    Activations Density 0.018%

    No Known Activations