© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-ATT-KK
    11. 3107
    Prev
    Next
    INDEX
    Explanations

    locations and geographical names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.11
    2:0.02
    3:0.02
    4:0.02
    5:0.41
    6:0.04
    7:0.01
    8:0.03
    9:0.11
    10:0.10
    11:0.05
    Negative Logits
     sugg
    -1.66
     facult
    -1.59
     description
    -1.47
    quant
    -1.45
    Inv
    -1.43
    Jeremy
    -1.39
    20439
    -1.37
     introdu
    -1.37
     acknowled
    -1.37
     Loki
    -1.36
    POSITIVE LOGITS
     peninsula
    2.10
     Chinatown
    2.07
     Valley
    2.06
     Cathedral
    2.03
    chester
    2.01
    borough
    1.93
    atown
    1.93
     Township
    1.86
     borough
    1.83
     streets
    1.81
    Activations Density 0.533%

    No Known Activations