© 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 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. 20993
    Prev
    Next
    INDEX
    Explanations

    mentions of social media interactions

    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
    0:0.17
    1:0.02
    2:0.02
    3:0.05
    4:0.09
    5:0.11
    6:0.04
    7:0.07
    8:0.03
    9:0.27
    10:0.01
    11:0.06
    Negative Logits
     Osc
    -2.65
     externalToEVAOnly
    -2.30
    ixon
    -2.27
     cob
    -2.27
     Magnet
    -2.19
     toss
    -2.16
     Mutant
    -2.14
     Libyan
    -2.12
     Gaddafi
    -2.12
     Cloak
    -2.11
    POSITIVE LOGITS
    �
    3.54
     ›
    2.90
    ibaba
    2.78
     are
    2.73
    Elsa
    2.62
     �
    2.61
     Elsa
    2.58
     Blizz
    2.52
     concerns
    2.51
     dragons
    2.46
    Activations Density 0.021%

    No Known Activations