© 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. 10-ATT-KK
    6. 12607
    Prev
    Next
    INDEX
    Explanations

    statements regarding police incidents and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.20
    1:0.10
    2:0.08
    3:0.05
    4:0.03
    5:0.03
    6:0.12
    7:0.09
    8:0.02
    9:0.04
    10:0.14
    11:0.04
    Negative Logits
    ø
    -3.32
     pengu
    -3.31
     SPD
    -3.25
     Antarctic
    -3.18
     gobl
    -3.16
     GNOME
    -3.12
    idepress
    -2.98
     Baltic
    -2.93
     Eston
    -2.89
    Py
    -2.84
    POSITIVE LOGITS
     Herrera
    10.05
     Guerrero
    4.09
    quez
    3.94
     Hernandez
    3.80
    rera
    3.80
    Mex
    3.77
     Mexican
    3.73
     Mata
    3.65
     Valencia
    3.65
     Reyes
    3.55
    Activations Density 0.002%

    No Known Activations