© 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. 9656
    Prev
    Next
    INDEX
    Explanations

    features and updates related to software or application functionalities

    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
    0:0.17
    1:0.13
    2:0.09
    3:0.04
    4:0.03
    5:0.02
    6:0.09
    7:0.09
    8:0.02
    9:0.04
    10:0.18
    11:0.04
    Negative Logits
     Tuc
    -3.30
     Oro
    -3.29
     Hig
    -3.11
     nec
    -3.05
     helic
    -2.98
     Lorenzo
    -2.83
     Scientology
    -2.77
     pont
    -2.75
     Reyn
    -2.73
     Gi
    -2.71
    POSITIVE LOGITS
     Dash
    9.95
    Dash
    8.98
    dash
    7.74
     dash
    6.48
     dashboard
    3.96
    Rush
    3.32
    ASH
    3.20
     cryptocurrency
    3.19
     DP
    3.14
     Shards
    3.13
    Activations Density 0.006%

    No Known Activations