© 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. 43952
    Prev
    Next
    INDEX
    Explanations

    mentions of television stations and media affiliations

    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
    0:0.03
    1:0.03
    2:0.06
    3:0.05
    4:0.05
    5:0.04
    6:0.08
    7:0.27
    8:0.02
    9:0.04
    10:0.18
    11:0.11
    Negative Logits
     advantages
    -1.66
     サーティワン
    -1.56
     trademarks
    -1.54
     lawy
    -1.53
     exemptions
    -1.52
     passwords
    -1.52
     enriched
    -1.50
     merits
    -1.49
     investments
    -1.47
     benefits
    -1.45
    POSITIVE LOGITS
    CTV
    2.02
     Burnett
    1.51
     NPR
    1.51
    nw
    1.50
     Toledo
    1.49
     Hue
    1.45
    umbn
    1.45
     Voice
    1.44
    CBS
    1.41
     Constable
    1.41
    Activations Density 0.005%

    No Known Activations