© 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. 14201
    Prev
    Next
    INDEX
    Explanations

    references to sports agents and signings related to defensive ends

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

    discussions around free agency and player signings in sports contexts

    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
    1:0.04
    2:0.08
    3:0.11
    4:0.02
    5:0.06
    6:0.10
    7:0.22
    8:0.06
    9:0.03
    10:0.09
    11:0.11
    Negative Logits
    mast
    -1.17
    xual
    -1.15
    yip
    -1.14
    esville
    -1.08
    �
    -1.08
     seiz
    -1.04
     dehuman
    -1.03
    erb
    -1.02
     orally
    -1.01
    �
    -1.00
    POSITIVE LOGITS
    ADA
    1.47
     waivers
    1.24
    guards
    1.24
     contingency
    1.21
     gamb
    1.20
    ��極
    1.17
    guard
    1.16
    charg
    1.13
     offseason
    1.11
     signings
    1.05
    Activations Density 0.010%

    No Known Activations