© 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. 16998
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting indicators in text

    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
    0:0.06
    1:0.05
    2:0.05
    3:0.05
    4:0.06
    5:0.05
    6:0.16
    7:0.05
    8:0.06
    9:0.28
    10:0.04
    11:0.04
    Negative Logits
    po
    -3.47
     raft
    -3.34
     Sail
    -3.28
     TP
    -3.14
    さ
    -3.08
     siph
    -3.02
     Roosevelt
    -3.01
     Symphony
    -2.96
     mushroom
    -2.96
    plom
    -2.96
    POSITIVE LOGITS
     Darren
    8.91
    Dar
    6.56
    dar
    4.91
     Dar
    4.29
     Barnett
    4.17
     Angus
    4.06
     Shaun
    3.98
     Aber
    3.86
     Nur
    3.66
     DAR
    3.57
    Activations Density 0.000%

    No Known Activations