© 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. 11856
    Prev
    Next
    INDEX
    Explanations

    information related to numbers and quantities

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

    quantitative values and counts related to various subjects

    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
    0:0.03
    1:0.02
    2:0.13
    3:0.06
    4:0.02
    5:0.03
    6:0.28
    7:0.07
    8:0.07
    9:0.03
    10:0.07
    11:0.14
    Negative Logits
    enance
    -1.35
     Uriel
    -1.24
     ANG
    -1.22
    ylum
    -1.21
     Voice
    -1.20
    Dialogue
    -1.18
     Ernst
    -1.15
    ILA
    -1.14
    actionDate
    -1.12
     Cros
    -1.12
    POSITIVE LOGITS
     apiece
    1.41
     increments
    1.31
    pointers
    1.14
    landers
    1.10
    coded
    1.09
     gallon
    1.09
     commandments
    1.09
    adian
    1.05
    renheit
    1.03
     rounds
    1.03
    Activations Density 0.106%

    No Known Activations