© 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. 10-ATT-KK
    11. 7210
    Prev
    Next
    INDEX
    Explanations

    references to studies and surveys related to socio-economic topics

    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
    0:0.12
    1:0.10
    2:0.07
    3:0.08
    4:0.08
    5:0.02
    6:0.12
    7:0.09
    8:0.03
    9:0.05
    10:0.08
    11:0.10
    Negative Logits
    acebook
    -3.02
     Polk
    -2.98
     Webs
    -2.82
     Zuckerberg
    -2.82
     hasht
    -2.77
     Snapchat
    -2.72
     Facebook
    -2.67
     accountability
    -2.57
    govern
    -2.56
     messaging
    -2.56
    POSITIVE LOGITS
    cised
    3.42
    cin
    2.96
    Heat
    2.88
    iris
    2.81
    ioxide
    2.79
    utonium
    2.72
    pha
    2.66
    heat
    2.52
     ammonia
    2.42
    amus
    2.42
    Activations Density 0.001%

    No Known Activations