© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 20748
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to software and IT services

    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
    0:0.12
    1:0.02
    2:0.04
    3:0.05
    4:0.30
    5:0.04
    6:0.04
    7:0.12
    8:0.02
    9:0.08
    10:0.03
    11:0.08
    Negative Logits
     fright
    -2.80
     torment
    -2.51
     slander
    -2.48
    ?]
    -2.46
    autions
    -2.38
     stricken
    -2.33
     disgrace
    -2.33
     hurts
    -2.33
     [*
    -2.28
     evils
    -2.28
    POSITIVE LOGITS
     computational
    4.15
     algorithms
    3.98
     scalable
    3.81
     optimization
    3.79
     algorith
    3.63
     APIs
    3.57
     IoT
    3.55
     optimized
    3.50
     automate
    3.48
     automation
    3.43
    Activations Density 0.687%

    No Known Activations