© 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. 5-ATT-KK
    11. 44562
    Prev
    Next
    INDEX
    Explanations

    mentions of Donald Trump

    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
    2:0.06
    3:0.16
    4:0.13
    5:0.03
    6:0.09
    7:0.07
    8:0.20
    9:0.06
    10:0.05
    11:0.06
    Negative Logits
    lished
    -1.80
     GOODMAN
    -1.69
    APTER
    -1.65
     =================================
    -1.59
    nikov
    -1.59
     toget
    -1.58
    $.
    -1.55
    ¶
    -1.50
     mosqu
    -1.46
     Chains
    -1.45
    POSITIVE LOGITS
    Bridge
    1.59
     Beach
    1.37
    ]]
    1.36
     Kavanaugh
    1.35
     ])
    1.35
    ��
    1.34
    wise
    1.33
    effic
    1.33
     Treasurer
    1.31
    appropriate
    1.29
    Activations Density 0.000%

    No Known Activations