© 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. 3-ATT-KK
    11. 5561
    Prev
    Next
    INDEX
    Explanations

    references to varying opinions and perspectives in discussions

    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
    0:0.02
    1:0.03
    2:0.16
    3:0.02
    4:0.01
    5:0.03
    6:0.28
    7:0.07
    8:0.03
    9:0.05
    10:0.06
    11:0.18
    Negative Logits
    ahime
    -1.28
     TAMADRA
    -1.22
    yssey
    -1.13
    atever
    -1.12
    /+
    -1.07
    ween
    -1.03
     Any
    -1.03
    creation
    -1.02
    agonist
    -1.01
    undown
    -1.00
    POSITIVE LOGITS
     unconsciously
    0.99
    frog
    0.97
     iP
    0.96
     approx
    0.95
     antidepressants
    0.94
    ihar
    0.93
    idas
    0.92
     physi
    0.92
     resembling
    0.91
    969
    0.90
    Activations Density 0.150%

    No Known Activations