© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 39771
    Prev
    Next
    INDEX
    Explanations

    pronouns and their corresponding verb forms indicating actions or states

    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
    0:0.01
    1:0.02
    2:0.05
    3:0.18
    4:0.14
    5:0.04
    6:0.12
    7:0.10
    8:0.07
    9:0.05
    10:0.07
    11:0.08
    Negative Logits
    ibaba
    -1.56
    ゴン
    -1.53
    �
    -1.42
    Ti
    -1.37
    furt
    -1.35
    oco
    -1.34
    detail
    -1.32
    pedia
    -1.32
    swers
    -1.32
    OIL
    -1.31
    POSITIVE LOGITS
     mentally
    1.36
     retire
    1.32
     sane
    1.26
    acles
    1.26
     minded
    1.25
     contrace
    1.25
     subconscious
    1.24
     rational
    1.23
     someday
    1.23
     dement
    1.22
    Activations Density 0.022%

    No Known Activations