© 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. 20457
    Prev
    Next
    INDEX
    Explanations

    lists of rankings and top entries in various categories

    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
    0:0.06
    1:0.09
    2:0.16
    3:0.08
    4:0.04
    5:0.04
    6:0.09
    7:0.09
    8:0.04
    9:0.07
    10:0.07
    11:0.13
    Negative Logits
    displayText
    -3.11
    ustomed
    -2.66
     Nadu
    -2.65
    ACTED
    -2.49
     prol
    -2.41
    �
    -2.40
     null
    -2.39
    ça
    -2.28
     counseling
    -2.27
     behavi
    -2.27
    POSITIVE LOGITS
     Top
    4.08
    Top
    3.58
     TOP
    3.30
    #
    3.23
    TOP
    3.21
     rankings
    3.11
     ranked
    3.11
    Rank
    3.03
     list
    3.02
     lists
    2.92
    Activations Density 0.056%

    No Known Activations