© 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. 21578
    Prev
    Next
    INDEX
    Explanations

    dates and specific numerical references associated with events

    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
    0:0.04
    1:0.02
    2:0.16
    3:0.04
    4:0.33
    5:0.05
    6:0.03
    7:0.02
    8:0.03
    9:0.15
    10:0.05
    11:0.02
    Negative Logits
    SourceFile
    -1.49
     constant
    -1.43
    ctors
    -1.40
    orously
    -1.35
    fast
    -1.33
    orous
    -1.31
    bling
    -1.28
    iping
    -1.27
    rawdownloadcloneembedreportprint
    -1.27
     wit
    -1.27
    POSITIVE LOGITS
    Interstitial
    2.18
    bourg
    1.56
    rosso
    1.55
    pring
    1.45
     advis
    1.43
    imester
    1.40
    ramid
    1.38
    ��
    1.38
    WARD
    1.34
    ODY
    1.33
    Activations Density 0.032%

    No Known Activations