© 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. 2-ATT-KK
    11. 12826
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and laboratory experiments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.21
    2:0.04
    3:0.05
    4:0.03
    5:0.06
    6:0.10
    7:0.12
    8:0.04
    9:0.06
    10:0.11
    11:0.06
    Negative Logits
    ulhu
    -1.92
    Ted
    -1.67
    WARE
    -1.67
    hello
    -1.66
     dime
    -1.66
     boiler
    -1.62
    Secure
    -1.61
    Private
    -1.59
    Civil
    -1.59
     yours
    -1.56
    POSITIVE LOGITS
     ∼
    2.88
     supplementation
    2.78
     biomark
    2.75
     β
    2.65
    ‐
    2.55
     (−
    2.48
     phenotype
    2.45
     mediated
    2.45
     endogenous
    2.41
     α
    2.35
    Activations Density 0.269%

    No Known Activations