© 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. 18024
    Prev
    Next
    INDEX
    Explanations

    special character sequences or symbols that may indicate non-standard text formatting

    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
    0:0.04
    1:0.02
    2:0.04
    3:0.09
    4:0.03
    5:0.05
    6:0.13
    7:0.04
    8:0.04
    9:0.11
    10:0.05
    11:0.29
    Negative Logits
     Mig
    -3.63
     ---
    -3.02
     "...
    -2.88
     --
    -2.51
     planner
    -2.51
     ``
    -2.50
     pods
    -2.38
     exploit
    -2.35
    .]
    -2.34
    :]
    -2.30
    POSITIVE LOGITS
    ·
    5.55
    €
    5.55
    £
    5.49
    ¢
    4.87
    «
    4.83
    ¨
    4.66
    â
    4.64
    ±
    4.57
    −
    4.55
    ©
    4.52
    Activations Density 0.001%

    No Known Activations