© 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. 9434
    Prev
    Next
    INDEX
    Explanations

    warnings or errors related to code implementation

    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
    0:0.07
    1:0.07
    2:0.07
    3:0.09
    4:0.09
    5:0.06
    6:0.11
    7:0.12
    8:0.05
    9:0.05
    10:0.10
    11:0.07
    Negative Logits
     Chak
    -1.02
     Sim
    -0.90
     Euras
    -0.87
     Ruler
    -0.85
    uras
    -0.84
     Garry
    -0.83
     Eucl
    -0.82
    grain
    -0.82
     Boh
    -0.82
     inev
    -0.81
    POSITIVE LOGITS
    restling
    1.19
    OTAL
    1.13
    LEASE
    1.12
    udeb
    1.11
    lucent
    1.10
    FINE
    1.08
    estic
    1.04
    EGIN
    1.03
    paren
    1.02
    ertodd
    1.02
    Activations Density 0.083%

    No Known Activations