© 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. 9-ATT-KK
    11. 17083
    Prev
    Next
    INDEX
    Explanations

    mentions of social media interactions and conversations

    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
    0:0.04
    1:0.02
    2:0.05
    3:0.04
    4:0.06
    5:0.05
    6:0.13
    7:0.04
    8:0.05
    9:0.42
    10:0.02
    11:0.03
    Negative Logits
     Din
    -3.44
     Tanz
    -3.36
    htar
    -3.31
    フォ
    -3.29
     Tid
    -3.28
     plantations
    -3.27
    ourt
    -3.25
    enth
    -3.22
     Harvest
    -3.21
    iths
    -3.20
    POSITIVE LOGITS
    Mike
    8.48
     Mike
    8.47
    ike
    4.82
     Mau
    4.46
     Pike
    4.37
    ikes
    4.24
    MJ
    4.16
     Moose
    4.13
     Maurice
    4.11
     Moe
    4.10
    Activations Density 0.014%

    No Known Activations