© 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. 4337
    Prev
    Next
    INDEX
    Explanations

    technical specifications and measurements related to firearms and their accessories

    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
    0:0.22
    1:0.05
    2:0.07
    3:0.14
    4:0.04
    5:0.13
    6:0.03
    7:0.04
    8:0.05
    9:0.03
    10:0.04
    11:0.10
    Negative Logits
     backlog
    -2.15
     chromosomes
    -2.09
     songs
    -2.03
    yrights
    -1.97
     chromosome
    -1.96
     craw
    -1.95
     downloaded
    -1.94
     downloading
    -1.92
     uploading
    -1.86
     subpoen
    -1.85
    POSITIVE LOGITS
    mm
    2.49
     Nato
    2.30
     NATO
    2.28
     SM
    2.19
     Leica
    2.18
     Telesc
    2.17
     CHR
    2.12
     Indust
    2.12
     MF
    2.07
    EVA
    2.05
    Activations Density 0.042%

    No Known Activations