© 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. 16517
    Prev
    Next
    INDEX
    Explanations

    instances of unique or special characters or symbols

    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
    0:0.09
    1:0.05
    2:0.07
    3:0.05
    4:0.05
    5:0.05
    6:0.18
    7:0.05
    8:0.08
    9:0.17
    10:0.05
    11:0.05
    Negative Logits
    Anderson
    -4.29
     Pru
    -4.28
     Anderson
    -3.97
     Russo
    -3.60
     Patton
    -3.58
    ovi
    -3.56
     Sullivan
    -3.50
    Sullivan
    -3.47
    osi
    -3.46
     Lean
    -3.40
    POSITIVE LOGITS
     Hex
    9.21
     hex
    7.86
    hex
    7.37
     oct
    4.83
     chrom
    4.30
     Dex
    4.06
     Hyd
    4.00
     Chrom
    3.82
     Nept
    3.80
     glyph
    3.80
    Activations Density 0.000%

    No Known Activations