© 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. 9-ATT-KK
    11. 2301
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with states and measures, particularly in statistics or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.56
    2:0.02
    3:0.04
    4:0.02
    5:0.04
    6:0.05
    7:0.03
    8:0.02
    9:0.06
    10:0.02
    11:0.04
    Negative Logits
    729
    -2.70
     Dragonbound
    -2.65
     gladly
    -2.42
    dayName
    -2.41
     lowly
    -2.40
    raq
    -2.39
    eers
    -2.39
    anwhile
    -2.38
     numer
    -2.35
     curiously
    -2.34
    POSITIVE LOGITS
    16
    4.07
     16
    3.94
    17
    3.37
     17
    3.11
    15
    3.10
     15
    2.96
    165
    2.83
    2016
    2.81
    cius
    2.71
     sixteen
    2.67
    Activations Density 0.027%

    No Known Activations