© 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. 22528
    Prev
    Next
    INDEX
    Explanations

    terms related to news articles reporting on events or situations involving people

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

    references to individuals involved in incidents or events, particularly regarding crime and investigation

    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
    0:0.06
    1:0.04
    2:0.06
    3:0.09
    4:0.02
    5:0.24
    6:0.07
    7:0.06
    8:0.11
    9:0.05
    10:0.11
    11:0.05
    Negative Logits
     latt
    -1.16
    ゴン
    -1.11
     Gil
    -1.01
     burner
    -1.01
     Potato
    -1.01
    plet
    -1.01
     Cannes
    -1.00
     mush
    -0.97
     Bliss
    -0.97
     Mell
    -0.96
    POSITIVE LOGITS
    ardless
    1.07
     shouldn
    1.07
    Crime
    1.06
    nob
    1.05
    Net
    1.05
    facebook
    1.04
    seless
    1.04
    BER
    1.03
    rac
    1.00
    eren
    1.00
    Activations Density 0.237%

    No Known Activations