© 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. 16483
    Prev
    Next
    INDEX
    Explanations

    references to specific newspapers and publications

    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
    0:0.02
    1:0.02
    2:0.02
    3:0.05
    4:0.06
    5:0.24
    6:0.02
    7:0.06
    8:0.02
    9:0.35
    10:0.02
    11:0.07
    Negative Logits
     defeats
    -2.44
     uninterrupted
    -2.40
     absence
    -2.39
     Archdemon
    -2.31
     maximize
    -2.16
     whichever
    -2.08
     emergencies
    -2.06
     widest
    -2.05
     whilst
    -2.04
    %%%%
    -2.02
    POSITIVE LOGITS
     entitled
    3.67
     titled
    3.26
     called
    3.04
    itled
    2.96
     dated
    2.67
     Called
    2.58
     labeled
    2.51
    named
    2.49
     headlined
    2.45
     written
    2.42
    Activations Density 0.026%

    No Known Activations