© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 4814
    Prev
    Next
    INDEX
    Explanations

    country names and their corresponding statistics or characteristics

    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
    0:0.03
    1:0.44
    2:0.03
    3:0.06
    4:0.03
    5:0.15
    6:0.02
    7:0.04
    8:0.05
    9:0.03
    10:0.02
    11:0.05
    Negative Logits
    each
    -2.81
    izoph
    -2.70
     hurd
    -2.69
    ieu
    -2.62
     merciless
    -2.54
    chie
    -2.47
     utmost
    -2.47
     dogged
    -2.42
    hou
    -2.42
     persistence
    -2.33
    POSITIVE LOGITS
    dayName
    3.41
    por
    2.90
    ocre
    2.87
    č
    2.82
    ר
    2.69
    apest
    2.62
    arth
    2.58
    thouse
    2.57
    zag
    2.57
    opens
    2.56
    Activations Density 0.004%

    No Known Activations