© 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. 14199
    Prev
    Next
    INDEX
    Explanations

    medical and health-related information, locations, and people involved in controversies

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

    themes related to social justice issues and historical discrimination

    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
    0:0.05
    1:0.12
    2:0.08
    3:0.03
    4:0.07
    5:0.15
    6:0.07
    7:0.08
    8:0.07
    9:0.06
    10:0.09
    11:0.07
    Negative Logits
    roxy
    -1.44
     tack
    -1.41
     manual
    -1.41
     instincts
    -1.41
    lde
    -1.33
     relent
    -1.32
     Rolls
    -1.32
     withdrawals
    -1.31
     graded
    -1.30
     quieter
    -1.30
    POSITIVE LOGITS
    装
    1.64
    arthed
    1.64
    malink
    1.60
    �
    1.57
    osate
    1.52
    �
    1.50
    ーティ
    1.49
    ydia
    1.49
     pione
    1.48
    �
    1.47
    Activations Density 0.403%

    No Known Activations