© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44616
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, particularly related to "South" and "North."

    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
    0:0.05
    1:0.10
    2:0.04
    3:0.04
    4:0.04
    5:0.29
    6:0.04
    7:0.03
    8:0.05
    9:0.07
    10:0.15
    11:0.06
    Negative Logits
    hor
    -2.01
    bda
    -1.98
    clips
    -1.93
    minus
    -1.88
    hello
    -1.82
    unic
    -1.81
    fig
    -1.77
    overs
    -1.76
    fortune
    -1.74
    wra
    -1.71
    POSITIVE LOGITS
    abama
    1.92
     Pradesh
    1.92
     electorate
    1.90
     Georgia
    1.88
     Queensland
    1.87
     coastline
    1.83
     Maine
    1.82
     Presidency
    1.81
     Georgian
    1.81
     Tex
    1.76
    Activations Density 0.003%

    No Known Activations