© 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. 5-ATT-KK
    11. 41821
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographic areas and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.01
    2:0.16
    3:0.15
    4:0.12
    5:0.04
    6:0.06
    7:0.06
    8:0.04
    9:0.07
    10:0.15
    11:0.06
    Negative Logits
     sacrifices
    -1.43
     perf
    -1.30
     Powell
    -1.30
     whistleblower
    -1.30
     Teresa
    -1.29
     Pearl
    -1.27
     Barney
    -1.27
     Pratt
    -1.27
     Newsp
    -1.27
     [*
    -1.25
    POSITIVE LOGITS
    kaya
    1.78
    malink
    1.58
    etsk
    1.58
    area
    1.55
    pop
    1.53
    widget
    1.50
    culosis
    1.49
    Status
    1.49
    western
    1.46
    ベ
    1.44
    Activations Density 0.007%

    No Known Activations