© 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. 10326
    Prev
    Next
    INDEX
    Explanations

    positive aspects and functionality of tech devices

    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
    0:0.05
    1:0.11
    2:0.10
    3:0.05
    4:0.09
    5:0.06
    6:0.15
    7:0.09
    8:0.04
    9:0.07
    10:0.08
    11:0.05
    Negative Logits
     partName
    -2.63
     CLR
    -2.63
    soDeliveryDate
    -2.62
    TM
    -2.59
     000
    -2.59
    aird
    -2.50
     Lori
    -2.49
    UTE
    -2.49
     Hath
    -2.47
     @@
    -2.47
    POSITIVE LOGITS
     Pros
    5.31
    Pros
    5.24
    Cons
    3.98
     Cons
    3.85
     pros
    3.70
     cons
    3.25
     Ner
    2.99
    cons
    2.81
     CONS
    2.75
    grades
    2.59
    Activations Density 0.001%

    No Known Activations