© 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. 15350
    Prev
    Next
    INDEX
    Explanations

    references to air and water

    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
    0:0.07
    1:0.13
    2:0.07
    3:0.05
    4:0.07
    5:0.03
    6:0.14
    7:0.12
    8:0.03
    9:0.06
    10:0.09
    11:0.11
    Negative Logits
    oro
    -2.73
    otine
    -2.67
     ut
    -2.64
     behavior
    -2.62
    aughtered
    -2.58
     Assist
    -2.57
    aze
    -2.56
    aido
    -2.53
     behavioral
    -2.41
    etooth
    -2.39
    POSITIVE LOGITS
    Anth
    3.02
     Corps
    2.78
     Garry
    2.75
    Cos
    2.71
     Col
    2.62
     Herm
    2.56
     Cos
    2.53
    creator
    2.51
     Commander
    2.41
     Colonel
    2.41
    Activations Density 0.000%

    No Known Activations