© 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. 46098
    Prev
    Next
    INDEX
    Explanations

    collective pronouns indicating unity or commonality

    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
    2:0.17
    3:0.14
    4:0.11
    5:0.03
    6:0.06
    7:0.10
    8:0.06
    9:0.06
    10:0.09
    11:0.09
    Negative Logits
    $.
    -1.42
     Lump
    -1.33
     Curve
    -1.30
     Fam
    -1.26
     clue
    -1.25
     Furious
    -1.25
    ItemTracker
    -1.24
     Phen
    -1.22
     Maid
    -1.19
    hemat
    -1.17
    POSITIVE LOGITS
    bleacher
    1.41
    APD
    1.33
    Ni
    1.31
    )"
    1.29
    odon
    1.26
    Additional
    1.25
    Alternatively
    1.22
    weeney
    1.22
    Featured
    1.19
    Please
    1.18
    Activations Density 0.000%

    No Known Activations