© 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. 8718
    Prev
    Next
    INDEX
    Explanations

    references to organizations, groups, or affiliations in parentheses

    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
    0:0.11
    1:0.11
    2:0.07
    3:0.07
    4:0.08
    5:0.03
    6:0.11
    7:0.11
    8:0.03
    9:0.05
    10:0.06
    11:0.12
    Negative Logits
     Militia
    -3.10
     Patriot
    -2.93
     security
    -2.85
     bombing
    -2.75
     terrorism
    -2.74
     Nato
    -2.71
     Security
    -2.68
     militia
    -2.68
     terrorist
    -2.66
     Patrol
    -2.65
    POSITIVE LOGITS
    aceae
    3.16
    Lens
    2.90
    ウス
    2.79
    olor
    2.74
    ilantro
    2.66
    gebra
    2.62
    Bloom
    2.57
    fried
    2.56
    icol
    2.53
    ohm
    2.53
    Activations Density 0.001%

    No Known Activations