© 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. 9-ATT-KK
    11. 9019
    Prev
    Next
    INDEX
    Explanations

    statistics related to immigration and deportation trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.03
    2:0.09
    3:0.33
    4:0.04
    5:0.12
    6:0.03
    7:0.06
    8:0.04
    9:0.03
    10:0.10
    11:0.03
    Negative Logits
     Zah
    -1.93
     girlfriend
    -1.82
     exorc
    -1.81
    crazy
    -1.79
    Eva
    -1.79
    something
    -1.77
    Laughs
    -1.76
     Canaver
    -1.76
    Brave
    -1.75
     mastermind
    -1.75
    POSITIVE LOGITS
     averages
    3.42
     probabilities
    3.32
     percentages
    3.25
     totals
    3.09
     averaged
    3.09
     estimates
    3.04
     percentage
    2.91
     ratios
    2.90
     average
    2.88
     estimate
    2.84
    Activations Density 1.003%

    No Known Activations