© 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. 9-ATT-KK
    11. 13410
    Prev
    Next
    INDEX
    Explanations

    elements related to social interactions and community sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.45
    2:0.04
    3:0.05
    4:0.04
    5:0.03
    6:0.04
    7:0.11
    8:0.03
    9:0.05
    10:0.04
    11:0.03
    Negative Logits
    imum
    -2.65
    imon
    -2.56
    iev
    -2.53
     Idol
    -2.50
     optimal
    -2.49
    dain
    -2.45
    ife
    -2.43
    isi
    -2.41
    ide
    -2.41
     optimum
    -2.39
    POSITIVE LOGITS
     partly
    7.59
     partially
    6.17
    mostly
    4.97
     mostly
    4.76
     chiefly
    4.63
     Mostly
    4.62
     largely
    4.62
     mainly
    4.61
     principally
    4.09
     wholly
    3.96
    Activations Density 0.014%

    No Known Activations