© 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. 2-ATT-KK
    11. 23297
    Prev
    Next
    INDEX
    Explanations

    text related to current events, political commentary, international affairs, fictional dialogue, and medical emergencies

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

    negative contractions and their usage in statements about uncertainty or inability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.01
    2:0.06
    3:0.08
    4:0.41
    5:0.05
    6:0.03
    7:0.02
    8:0.06
    9:0.06
    10:0.04
    11:0.02
    Negative Logits
     Jav
    -1.51
     Gou
    -1.43
     Lad
    -1.43
    Gra
    -1.39
     guid
    -1.33
     Gram
    -1.33
     bye
    -1.32
     Pwr
    -1.30
    lez
    -1.30
    lift
    -1.30
    POSITIVE LOGITS
    bilt
    1.63
    antic
    1.58
    orks
    1.55
     stubborn
    1.43
    details
    1.43
    thouse
    1.43
     awaiting
    1.39
    tics
    1.39
     disagree
    1.38
     innocence
    1.37
    Activations Density 0.062%

    No Known Activations