© 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. 5-ATT-KK
    11. 5831
    Prev
    Next
    INDEX
    Explanations

    content related to legal and judicial proceedings or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.03
    1:0.02
    2:0.05
    3:0.08
    4:0.20
    5:0.04
    6:0.14
    7:0.08
    8:0.04
    9:0.07
    10:0.11
    11:0.08
    Negative Logits
     metabol
    -1.33
     eras
    -1.32
    abeth
    -1.32
     affili
    -1.32
     prosec
    -1.31
    resy
    -1.31
     UCHIJ
    -1.30
     respectively
    -1.30
     responsibilities
    -1.28
     fulfil
    -1.27
    POSITIVE LOGITS
    wang
    1.35
    Bay
    1.30
    pic
    1.29
    https
    1.27
    CB
    1.25
    http
    1.25
    =>
    1.24
     Unlimited
    1.24
    FT
    1.21
    tu
    1.21
    Activations Density 0.033%

    No Known Activations