© 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. 34641
    Prev
    Next
    INDEX
    Explanations

    programming or coding constructs related to user interfaces and data handling

    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
    0:0.10
    1:0.27
    2:0.04
    3:0.04
    4:0.03
    5:0.19
    6:0.06
    7:0.03
    8:0.04
    9:0.06
    10:0.05
    11:0.03
    Negative Logits
     GOODMAN
    -2.58
     AX
    -2.55
     LORD
    -2.24
     LONG
    -2.23
     FORM
    -2.22
     IND
    -2.21
     ABE
    -2.21
     DAY
    -2.19
     AG
    -2.13
     SEC
    -2.10
    POSITIVE LOGITS
    nl
    2.80
    utm
    2.54
    bum
    2.50
    rg
    2.48
    netflix
    2.47
    gor
    2.45
    obal
    2.40
    til
    2.37
    roma
    2.37
    ln
    2.36
    Activations Density 0.003%

    No Known Activations