© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 29890
    Prev
    Next
    INDEX
    Explanations

    negative connotations or opposition in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.03
    1:0.01
    2:0.20
    3:0.08
    4:0.05
    5:0.04
    6:0.10
    7:0.03
    8:0.18
    9:0.03
    10:0.05
    11:0.14
    Negative Logits
    flix
    -1.69
    ppings
    -1.59
    ktop
    -1.58
    ////////////////
    -1.55
    bid
    -1.44
    tera
    -1.43
    kai
    -1.42
    nings
    -1.40
    nai
    -1.37
    aido
    -1.35
    POSITIVE LOGITS
    CONCLUS
    1.43
     downright
    1.42
     CTR
    1.40
    "]=>
    1.39
     Prompt
    1.35
     empowering
    1.34
     Trafford
    1.31
    clinton
    1.30
    lete
    1.24
    redit
    1.24
    Activations Density 0.003%

    No Known Activations