© 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. 10-ATT-KK
    11. 14141
    Prev
    Next
    INDEX
    Explanations

    critical observations and statements about media influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.19
    1:0.06
    2:0.15
    3:0.06
    4:0.02
    5:0.02
    6:0.11
    7:0.10
    8:0.02
    9:0.03
    10:0.14
    11:0.05
    Negative Logits
    Sov
    -3.02
    ahar
    -2.73
     proble
    -2.72
     Vor
    -2.70
     DAC
    -2.68
    ija
    -2.68
    chedel
    -2.62
     Oslo
    -2.62
    ctica
    -2.61
    accompan
    -2.61
    POSITIVE LOGITS
     Fox
    9.69
    Fox
    9.30
     FOX
    7.22
    FOX
    6.88
    fox
    6.73
     fox
    6.40
     Murdoch
    4.66
     Hannity
    4.36
     Cable
    4.35
    Reilly
    4.23
    Activations Density 0.072%

    No Known Activations