© 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. 5-ATT-KK
    11. 46260
    Prev
    Next
    INDEX
    Explanations

    percentages and statistics related to public opinion in polling data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.11
    3:0.14
    4:0.09
    5:0.03
    6:0.03
    7:0.04
    8:0.04
    9:0.03
    10:0.15
    11:0.24
    Negative Logits
     cele
    -1.45
    ggle
    -1.42
     amen
    -1.24
     appl
    -1.21
     constitu
    -1.20
     champ
    -1.17
    livion
    -1.17
     darling
    -1.16
    favorite
    -1.14
    creen
    -1.14
    POSITIVE LOGITS
    PDF
    1.42
     Vec
    1.26
    RFC
    1.21
    ursion
    1.15
     trapping
    1.14
    Published
    1.11
     Duc
    1.08
     phased
    1.07
     Illegal
    1.06
    lethal
    1.04
    Activations Density 0.098%

    No Known Activations