© 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. 10-ATT-KK
    11. 16154
    Prev
    Next
    INDEX
    Explanations

    connector phrases and conjunctions within discussions of socio-political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.28
    2:0.09
    3:0.06
    4:0.03
    5:0.03
    6:0.06
    7:0.05
    8:0.03
    9:0.05
    10:0.06
    11:0.16
    Negative Logits
     shortened
    -3.10
     Neutral
    -3.08
     weakness
    -2.90
     neutral
    -2.85
     shortest
    -2.81
     Lat
    -2.79
     mascul
    -2.79
     convertible
    -2.76
     colder
    -2.70
     warmer
    -2.63
    POSITIVE LOGITS
     Thousands
    4.11
    Thousands
    3.86
     Hundreds
    3.68
    illions
    3.62
     Millions
    3.62
    ousands
    3.61
     thousands
    3.54
    Hundreds
    3.47
    million
    3.43
    undreds
    3.37
    Activations Density 0.001%

    No Known Activations