© 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. 22652
    Prev
    Next
    INDEX
    Explanations

    words related to preferences or choices made by individuals

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

    phrases and structures indicating preferences or choices

    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
    0:0.05
    1:0.02
    2:0.14
    3:0.05
    4:0.25
    5:0.06
    6:0.02
    7:0.02
    8:0.08
    9:0.18
    10:0.06
    11:0.03
    Negative Logits
    pload
    -1.65
    querque
    -1.59
    infeld
    -1.46
    loo
    -1.40
    rir
    -1.32
    kj
    -1.29
    umbai
    -1.28
    apeake
    -1.27
    azeera
    -1.25
    Rail
    -1.25
    POSITIVE LOGITS
    TEXTURE
    1.46
     overr
    1.38
    lihood
    1.37
     presets
    1.33
     fonts
    1.33
     Ratings
    1.31
     selections
    1.30
     Preferences
    1.29
     pleasing
    1.28
     preferences
    1.28
    Activations Density 0.005%

    No Known Activations