© 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. 3-ATT-KK
    11. 14461
    Prev
    Next
    INDEX
    Explanations

    objects that are described or used in drawing or illustrating, such as pencils

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    instances of the letter 's' or words containing the letter 's', especially in conjunction with writing tools like pencils

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.07
    3:0.25
    4:0.03
    5:0.04
    6:0.10
    7:0.15
    8:0.03
    9:0.07
    10:0.09
    11:0.06
    Negative Logits
    OTOS
    -1.29
    ONSORED
    -1.28
    imity
    -1.21
    ibling
    -1.21
    outheast
    -1.14
    CVE
    -1.13
    gain
    -1.13
    ENTION
    -1.12
    idays
    -1.12
     Pradesh
    -1.12
    POSITIVE LOGITS
    thur
    1.27
     wrist
    1.18
     slate
    1.15
     Motorola
    1.14
     professionally
    1.11
    GREEN
    1.11
     matte
    1.10
     wrists
    1.07
     wear
    1.06
     blot
    1.04
    Activations Density 0.001%

    No Known Activations