© 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. 5003
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to rankings and statistics

    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
    0:0.02
    1:0.53
    2:0.02
    3:0.04
    4:0.02
    5:0.07
    6:0.04
    7:0.03
    8:0.03
    9:0.06
    10:0.03
    11:0.05
    Negative Logits
     Sind
    -2.68
     sprink
    -2.59
    sted
    -2.50
    este
    -2.48
    ENDED
    -2.40
    idi
    -2.36
    ordes
    -2.36
     instead
    -2.35
     disbel
    -2.32
    instead
    -2.32
    POSITIVE LOGITS
    18
    4.00
    17
    3.39
    1800
    3.29
     18
    3.29
    1920
    2.89
    imentary
    2.88
     17
    2.85
    1900
    2.82
    herer
    2.82
     1840
    2.79
    Activations Density 0.015%

    No Known Activations