© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12213
    Prev
    Next
    INDEX
    Explanations

    locations in different parts of the world

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    geographic locations and places mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.11
    1:0.03
    2:0.03
    3:0.02
    4:0.43
    5:0.03
    6:0.08
    7:0.04
    8:0.03
    9:0.02
    10:0.09
    11:0.04
    Negative Logits
    merce
    -1.86
     conduc
    -1.83
    Downloadha
    -1.74
     ageing
    -1.73
     cabinet
    -1.67
     judiciary
    -1.64
     MLA
    -1.63
     backlog
    -1.63
     estate
    -1.62
     UD
    -1.61
    POSITIVE LOGITS
    asso
    2.18
    bol
    2.03
    rious
    1.91
    CLASSIFIED
    1.87
    iazep
    1.86
    VIDIA
    1.82
    eson
    1.80
    eval
    1.78
    SCP
    1.75
    rett
    1.75
    Activations Density 0.453%

    No Known Activations