© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43529
    Prev
    Next
    INDEX
    Explanations

    references to versions and software compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.06
    1:0.03
    2:0.13
    3:0.09
    4:0.06
    5:0.06
    6:0.04
    7:0.04
    8:0.07
    9:0.09
    10:0.16
    11:0.12
    Negative Logits
    fty
    -1.33
     Intent
    -1.19
    ickle
    -1.08
    sein
    -1.04
    catching
    -1.03
    ndra
    -1.03
     Manifest
    -1.01
    entious
    -1.00
    ela
    -0.99
     Pog
    -0.97
    POSITIVE LOGITS
    */
    1.20
    ���
    1.18
     Caucasus
    1.18
    MX
    1.17
     ATI
    1.17
     SLI
    1.16
     prefers
    1.12
    istar
    1.11
    addons
    1.09
    Recommended
    1.09
    Activations Density 0.139%

    No Known Activations