© 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. 22068
    Prev
    Next
    INDEX
    Explanations

    references to police actions and law enforcement activities

    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
    0:0.05
    1:0.07
    2:0.08
    3:0.06
    4:0.02
    5:0.07
    6:0.03
    7:0.07
    8:0.04
    9:0.29
    10:0.11
    11:0.06
    Negative Logits
    Moon
    -1.39
    isSpecialOrderable
    -1.36
    Quantity
    -1.28
    kiss
    -1.26
    ":"/
    -1.24
    �
    -1.22
    omorphic
    -1.20
     competitiveness
    -1.20
     geop
    -1.20
    Future
    -1.19
    POSITIVE LOGITS
    nsic
    1.73
     CCTV
    1.51
    iries
    1.51
    nsics
    1.51
     detectives
    1.50
     prosecution
    1.50
     Detect
    1.47
     detectors
    1.46
     investigating
    1.43
     informants
    1.43
    Activations Density 0.146%

    No Known Activations