© 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. 3-ATT-KK
    11. 13423
    Prev
    Next
    INDEX
    Explanations

    technical instructions and code snippets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    occurrences of the word "the" and variations of articles like "a" and "an"

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.03
    2:0.11
    3:0.19
    4:0.02
    5:0.04
    6:0.04
    7:0.09
    8:0.17
    9:0.16
    10:0.04
    11:0.04
    Negative Logits
    urd
    -1.21
    iggs
    -1.17
    piring
    -1.15
    ensable
    -1.13
    én
    -1.11
    urden
    -1.09
    ��
    -1.03
    ���
    -1.02
     ensued
    -1.02
    irement
    -1.01
    POSITIVE LOGITS
     IPM
    1.52
     sparing
    1.30
     quar
    1.11
    MSN
    1.11
     GOODMAN
    1.09
     interchange
    1.09
     alloc
    1.07
     notation
    1.04
     specially
    1.02
     Palest
    1.01
    Activations Density 0.059%

    No Known Activations