© 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. 40284
    Prev
    Next
    INDEX
    Explanations

    references to organizations and their statistics related to reproductive health

    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
    1:0.01
    2:0.09
    3:0.05
    4:0.03
    5:0.03
    6:0.13
    7:0.05
    8:0.05
    9:0.05
    10:0.38
    11:0.05
    Negative Logits
     tresp
    -2.24
    andals
    -1.98
     graffiti
    -1.83
     trespass
    -1.79
    kar
    -1.77
     Formation
    -1.77
    arov
    -1.76
     Beckham
    -1.76
    lda
    -1.76
    eric
    -1.75
    POSITIVE LOGITS
    Recommend
    1.95
    Universal
    1.94
     conclusions
    1.89
    Consumer
    1.83
     recommends
    1.81
     rejoice
    1.81
     charities
    1.80
     dinners
    1.75
    Premium
    1.73
     standards
    1.72
    Activations Density 0.000%

    No Known Activations