© 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. 9-ATT-KK
    11. 3829
    Prev
    Next
    INDEX
    Explanations

    references to pacing, completion, and operational readiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.05
    3:0.17
    4:0.02
    5:0.04
    6:0.02
    7:0.07
    8:0.03
    9:0.01
    10:0.45
    11:0.02
    Negative Logits
     imperfect
    -2.43
    but
    -2.40
     but
    -2.03
    albeit
    -1.92
     occasionally
    -1.84
     mistakes
    -1.82
     BUT
    -1.75
     misunderstood
    -1.71
    BUT
    -1.68
     slightly
    -1.65
    POSITIVE LOGITS
     nor
    2.52
     unanimous
    2.45
     anymore
    2.42
    "]=>
    2.17
    clusively
    2.16
     necessarily
    2.13
     guarantee
    2.08
     wholesale
    2.05
     definitively
    2.03
    estamp
    2.02
    Activations Density 0.542%

    No Known Activations