© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 16962
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0:0.08
    1:0.04
    2:0.06
    3:0.05
    4:0.06
    5:0.04
    6:0.21
    7:0.05
    8:0.07
    9:0.18
    10:0.05
    11:0.05
    Negative Logits
     Pharaoh
    -3.77
    utm
    -3.64
     Samsung
    -3.63
     Hyundai
    -3.62
    araoh
    -3.62
    anmar
    -3.45
    Samsung
    -3.17
     Ul
    -3.14
     Silk
    -3.07
    Park
    -3.05
    POSITIVE LOGITS
     Bord
    9.52
     Bridgewater
    4.53
    ord
    3.91
     Baz
    3.90
     Gord
    3.86
     Gard
    3.73
    Gall
    3.71
     Bett
    3.71
     Parm
    3.64
    Buff
    3.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.