© 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. 15337
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to discussions, details, and speculative assertions

    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
    0:0.02
    1:0.04
    2:0.05
    3:0.04
    4:0.06
    5:0.38
    6:0.02
    7:0.03
    8:0.02
    9:0.22
    10:0.02
    11:0.04
    Negative Logits
    accompan
    -2.86
     protects
    -2.73
     interacted
    -2.59
     supervised
    -2.58
     interacts
    -2.54
    ••••
    -2.48
     maintains
    -2.47
     regulates
    -2.41
     correlates
    -2.36
     varies
    -2.33
    POSITIVE LOGITS
     here
    4.11
     HERE
    3.62
     hereby
    3.35
     anymore
    3.31
    anity
    3.10
     myself
    3.03
    here
    2.98
    below
    2.98
     lightly
    2.97
    yet
    2.96
    Activations Density 0.054%

    No Known Activations