© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 23304
    Prev
    Next
    INDEX
    Explanations

    user-related indicators such as usernames, post counts, and location data

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.06
    1:0.06
    2:0.05
    3:0.04
    4:0.05
    5:0.11
    6:0.12
    7:0.10
    8:0.21
    9:0.04
    10:0.05
    11:0.06
    Negative Logits
    \<
    -2.84
    [/
    -2.54
    etheless
    -2.43
    -[
    -2.18
     corrid
    -2.17
     Pri
    -2.16
    senal
    -2.13
    ilion
    -2.12
     Paddock
    -2.11
    mpeg
    -2.11
    POSITIVE LOGITS
    Thread
    3.01
     threads
    2.71
    &
    2.58
     Topic
    2.43
    Premium
    2.40
     sclerosis
    2.33
    ined
    2.27
    Dutch
    2.19
    Member
    2.15
    monton
    2.15
    Activations Density 0.001%

    No Known Activations