© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14413
    Prev
    Next
    INDEX
    Explanations

    independent or alternative political perspectives

    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
    0:0.05
    1:0.33
    2:0.05
    3:0.05
    4:0.04
    5:0.02
    6:0.15
    7:0.08
    8:0.02
    9:0.04
    10:0.05
    11:0.06
    Negative Logits
     Spur
    -3.28
    bryce
    -2.63
     Hor
    -2.47
     aggrav
    -2.42
    acket
    -2.42
    CVE
    -2.38
    bol
    -2.36
    Whit
    -2.36
    Heat
    -2.31
    heat
    -2.30
    POSITIVE LOGITS
     independent
    7.41
     Independent
    7.10
    Independent
    7.10
    independent
    6.91
     independ
    6.20
     independence
    6.11
    independence
    5.62
     independents
    5.45
     independently
    5.29
     Independence
    4.82
    Activations Density 0.046%

    No Known Activations