© 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. 9062
    Prev
    Next
    INDEX
    Explanations

    references to specific tangible items or physical descriptors

    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
    0:0.04
    1:0.04
    2:0.08
    3:0.12
    4:0.09
    5:0.07
    6:0.03
    7:0.08
    8:0.03
    9:0.27
    10:0.04
    11:0.08
    Negative Logits
     visits
    -3.05
     individuals
    -2.91
     majorities
    -2.89
     members
    -2.86
     partners
    -2.85
     representatives
    -2.83
     affili
    -2.81
     departures
    -2.79
     peoples
    -2.79
     campaigns
    -2.79
    POSITIVE LOGITS
    rower
    3.58
    mite
    2.95
    keleton
    2.79
    slice
    2.70
    mitter
    2.67
    omaly
    2.66
    ��
    2.61
    trap
    2.60
    ressor
    2.60
    forcer
    2.58
    Activations Density 1.159%

    No Known Activations