© 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. 3-ATT-KK
    11. 13985
    Prev
    Next
    INDEX
    Explanations

    instances of advising or being advised, particularly related to official matters or decisions

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

    phrases related to advice or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.11
    3:0.14
    4:0.01
    5:0.03
    6:0.06
    7:0.12
    8:0.16
    9:0.12
    10:0.07
    11:0.09
    Negative Logits
     gra
    -0.94
    fman
    -0.88
     Nass
    -0.86
    zilla
    -0.82
     ont
    -0.82
     haunted
    -0.82
     marvel
    -0.81
     sunk
    -0.80
     Kimmel
    -0.80
     objectively
    -0.79
    POSITIVE LOGITS
    rolet
    1.19
    iquette
    0.97
    each
    0.91
    cerning
    0.89
     Helpful
    0.88
     counsel
    0.88
    hire
    0.87
     [*
    0.86
    urtle
    0.85
    覚醒
    0.85
    Activations Density 0.008%

    No Known Activations