© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10682
    Prev
    Next
    INDEX
    Explanations

    variations of the suffix "ing" and words rooted in academic or technical language

    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
    0:0.04
    1:0.03
    2:0.08
    3:0.34
    4:0.02
    5:0.02
    6:0.05
    7:0.16
    8:0.07
    9:0.05
    10:0.05
    11:0.05
    Negative Logits
    redit
    -1.32
    akespe
    -1.28
    atri
    -1.28
    sels
    -1.25
    PAC
    -1.21
    FactoryReloaded
    -1.20
    eport
    -1.20
    Vote
    -1.20
    �
    -1.19
    emouth
    -1.18
    POSITIVE LOGITS
     haste
    1.21
     midst
    1.20
     equation
    1.16
     womb
    1.15
    asca
    1.15
     tre
    1.13
     conversation
    1.12
     woods
    1.11
    cape
    1.11
     belt
    1.11
    Activations Density 0.024%

    No Known Activations