© 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. 4622
    Prev
    Next
    INDEX
    Explanations

    comparisons and evaluations related to battery performance and size

    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
    0:0.28
    1:0.01
    2:0.19
    3:0.11
    4:0.02
    5:0.11
    6:0.04
    7:0.05
    8:0.05
    9:0.03
    10:0.04
    11:0.02
    Negative Logits
     Hispan
    -2.86
     transsexual
    -2.66
     puppet
    -2.62
     Haitian
    -2.60
     Puppet
    -2.53
     pupp
    -2.48
     hierarch
    -2.47
     Robertson
    -2.37
     offic
    -2.37
    女
    -2.26
    POSITIVE LOGITS
     recharge
    6.12
     batteries
    5.42
    Battery
    5.21
     battery
    5.09
     lithium
    4.93
     charger
    4.90
     Battery
    4.52
    mAh
    4.29
     Lith
    4.25
     voltage
    4.21
    Activations Density 0.136%

    No Known Activations