© 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. 5-ATT-KK
    11. 45420
    Prev
    Next
    INDEX
    Explanations

    references to the State Department and its officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.05
    3:0.05
    4:0.05
    5:0.06
    6:0.06
    7:0.03
    8:0.03
    9:0.04
    10:0.39
    11:0.18
    Negative Logits
     Gree
    -1.68
     epile
    -1.62
     relapse
    -1.53
    arios
    -1.44
    rencies
    -1.43
    ife
    -1.43
     THC
    -1.37
    RANT
    -1.37
    lycer
    -1.36
    Redd
    -1.34
    POSITIVE LOGITS
     Secret
    1.63
     Adviser
    1.60
     Office
    1.56
     briefed
    1.54
    authorized
    1.48
     ®
    1.46
     authorised
    1.45
    Office
    1.44
     Advisor
    1.39
    olicited
    1.37
    Activations Density 0.012%

    No Known Activations