© 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. 10-ATT-KK
    11. 21538
    Prev
    Next
    INDEX
    Explanations

    words related to linguistic structures and pronunciations

    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
    0:0.14
    1:0.08
    2:0.06
    3:0.08
    4:0.07
    5:0.03
    6:0.08
    7:0.10
    8:0.07
    9:0.04
    10:0.07
    11:0.13
    Negative Logits
    agate
    -2.89
    resy
    -2.69
     Inquiry
    -2.62
     Rampage
    -2.59
    abilia
    -2.58
     Damien
    -2.55
     Thunderbolt
    -2.55
     WWF
    -2.53
     Wrestling
    -2.50
     Agenda
    -2.50
    POSITIVE LOGITS
     vowel
    5.00
     vow
    4.69
     conson
    4.59
     pronunciation
    4.05
     voic
    3.87
     phon
    3.58
     pronoun
    3.55
     pronounced
    3.40
     pron
    3.35
    phabet
    3.33
    Activations Density 0.014%

    No Known Activations