© 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. 8335
    Prev
    Next
    INDEX
    Explanations

    elements indicating ratings or evaluations of performance

    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
    0:0.21
    1:0.08
    2:0.07
    3:0.06
    4:0.04
    5:0.03
    6:0.08
    7:0.09
    8:0.04
    9:0.05
    10:0.14
    11:0.05
    Negative Logits
    ijk
    -3.40
    �
    -3.32
    覚醒
    -3.24
     Rah
    -3.23
    ijn
    -3.19
    zie
    -3.16
    �
    -3.10
    cycles
    -3.07
    olulu
    -3.00
    indal
    -2.93
    POSITIVE LOGITS
     Plex
    9.30
    Plex
    8.15
    plex
    5.36
     Kodi
    4.24
    Pod
    3.94
     Pod
    3.92
     Roku
    3.82
     RP
    3.81
     Puppet
    3.71
     Pupp
    3.45
    Activations Density 0.001%

    No Known Activations