© 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. 8355
    Prev
    Next
    INDEX
    Explanations

    proper nouns and their associations within contexts

    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
    0:0.10
    1:0.20
    2:0.06
    3:0.05
    4:0.03
    5:0.02
    6:0.07
    7:0.08
    8:0.15
    9:0.02
    10:0.13
    11:0.04
    Negative Logits
     unse
    -3.00
     tumble
    -2.42
     oval
    -2.38
     sob
    -2.32
     charms
    -2.27
    ulsive
    -2.23
     charm
    -2.22
     addict
    -2.19
     orderly
    -2.17
     clay
    -2.15
    POSITIVE LOGITS
    IF
    4.79
     IF
    4.26
    if
    4.00
    ifi
    3.43
    ouf
    3.36
    ifa
    3.23
    tif
    3.20
    IFF
    3.03
    EF
    3.02
    ef
    2.97
    Activations Density 0.001%

    No Known Activations