© 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. 3-ATT-KK
    11. 14106
    Prev
    Next
    INDEX
    Explanations

    political discussions and controversies involving prominent figures and elections

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

    references to political opinions and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.09
    2:0.06
    3:0.02
    4:0.09
    5:0.19
    6:0.07
    7:0.07
    8:0.06
    9:0.07
    10:0.11
    11:0.07
    Negative Logits
    .」
    -1.75
    cair
    -1.70
     civilisation
    -1.65
    ''.
    -1.62
    」
    -1.62
     Settlement
    -1.59
    .$
    -1.59
     liv
    -1.55
    aceae
    -1.55
     Located
    -1.53
    POSITIVE LOGITS
     retweet
    2.45
     rhetorical
    2.00
     insulting
    1.90
     sarcast
    1.90
    Tweet
    1.84
     debunked
    1.83
     misinterpret
    1.82
     praising
    1.79
     Kimmel
    1.75
     hypocrisy
    1.73
    Activations Density 0.491%

    No Known Activations