© 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. 10-ATT-KK
    11. 7442
    Prev
    Next
    INDEX
    Explanations

    references to technology and media availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    2:0.04
    3:0.04
    4:0.06
    5:0.53
    6:0.02
    7:0.03
    8:0.02
    9:0.11
    10:0.02
    11:0.04
    Negative Logits
     ONLY
    -4.42
    instead
    -4.24
     instead
    -3.95
    Instead
    -3.84
    SPONSORED
    -3.83
    only
    -3.77
    always
    -3.60
     ALWAYS
    -3.60
     Instead
    -3.55
     NEVER
    -3.54
    POSITIVE LOGITS
     enough
    2.72
    unci
    2.59
    enough
    2.42
    cellent
    2.38
    ahime
    2.33
    !:
    2.31
     recently
    2.31
    yang
    2.27
     sufficiently
    2.25
     underway
    2.18
    Activations Density 0.296%

    No Known Activations