© 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. 3-ATT-KK
    11. 11736
    Prev
    Next
    INDEX
    Explanations

    references to computer programming terms and discussions

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

    non-verbal content such as symbols or formatting cues in the text

    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
    0:0.02
    1:0.06
    2:0.07
    3:0.10
    4:0.03
    5:0.04
    6:0.07
    7:0.29
    8:0.05
    9:0.06
    10:0.05
    11:0.11
    Negative Logits
     knees
    -1.22
    stood
    -1.19
    sung
    -1.19
    sta
    -1.17
    egu
    -1.15
     contracted
    -1.15
     churn
    -1.13
     footh
    -1.13
    psey
    -1.12
     disg
    -1.12
    POSITIVE LOGITS
    Quotes
    1.68
    版
    1.58
    Characters
    1.48
     Explan
    1.41
     Advice
    1.35
    Applic
    1.33
    Reference
    1.33
    Recommend
    1.30
     Handbook
    1.28
     Names
    1.28
    Activations Density 0.121%

    No Known Activations