© 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. 4972
    Prev
    Next
    INDEX
    Explanations

    references to research studies and their findings

    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
    0:0.10
    1:0.03
    2:0.32
    3:0.10
    4:0.03
    5:0.09
    6:0.04
    7:0.06
    8:0.07
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
    ufact
    -3.32
     valves
    -3.28
     imports
    -3.15
     reservoirs
    -3.14
     rupt
    -2.91
     miners
    -2.89
     waterways
    -2.88
     contaminated
    -2.86
     repaired
    -2.84
     rupture
    -2.83
    POSITIVE LOGITS
     Psychology
    6.56
     psychologist
    6.24
     psychologists
    6.07
     psychology
    5.85
     Psychological
    5.85
    Psych
    5.46
     Psych
    5.25
     Behavioral
    4.94
    psych
    4.88
     Cognitive
    4.75
    Activations Density 0.031%

    No Known Activations