© 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. 2-ATT-KK
    11. 22642
    Prev
    Next
    INDEX
    Explanations

    technical information related to legal cases or political statements and discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating uncertainty or doubt about a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.20
    3:0.13
    4:0.11
    5:0.08
    6:0.05
    7:0.03
    8:0.07
    9:0.11
    10:0.06
    11:0.02
    Negative Logits
     runway
    -1.00
     arrivals
    -0.99
     Detention
    -0.98
    Roll
    -0.97
    Topics
    -0.94
    avanaugh
    -0.92
     fumble
    -0.91
     galaxies
    -0.90
     Hornets
    -0.88
     detention
    -0.87
    POSITIVE LOGITS
    achev
    1.16
    emonic
    1.10
     cheaper
    1.06
     Logged
    1.04
    ryu
    1.02
    zx
    1.01
    tk
    1.00
    onel
    1.00
    ngth
    1.00
     easiest
    1.00
    Activations Density 0.019%

    No Known Activations