© 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. 3-ATT-KK
    11. 14090
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and governmental actions

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

    phrases and characters related to financial and government regulations

    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
    0:0.10
    1:0.09
    2:0.11
    3:0.06
    4:0.04
    5:0.06
    6:0.09
    7:0.07
    8:0.13
    9:0.07
    10:0.08
    11:0.06
    Negative Logits
     lett
    -1.34
     welf
    -1.32
     Macintosh
    -1.21
     crafts
    -1.20
    isan
    -1.18
     debian
    -1.12
     cottage
    -1.11
     Clip
    -1.10
     worlds
    -1.09
     ['
    -1.08
    POSITIVE LOGITS
     Cosponsors
    1.48
     sidx
    1.30
    assium
    1.30
    ably
    1.27
     attm
    1.27
    rather
    1.23
    appropriately
    1.23
    ledged
    1.20
     indirectly
    1.19
    eligible
    1.18
    Activations Density 0.067%

    No Known Activations