© 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. 3-ATT-KK
    11. 11792
    Prev
    Next
    INDEX
    Explanations

    academic and political discourse related to socio-economic issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to socio-economic studies and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.02
    2:0.08
    3:0.12
    4:0.02
    5:0.04
    6:0.03
    7:0.08
    8:0.10
    9:0.16
    10:0.05
    11:0.23
    Negative Logits
    roximately
    -1.33
    ario
    -1.21
    ixie
    -1.16
    ello
    -1.14
    \-
    -1.14
    erity
    -1.13
    ère
    -1.12
    ople
    -1.12
    medium
    -1.12
    ovich
    -1.12
    POSITIVE LOGITS
     haunt
    1.45
     revisit
    1.39
     millenn
    1.31
     refreshed
    1.30
     revis
    1.23
     horm
    1.21
    dos
    1.19
     adolesc
    1.17
     vengeance
    1.17
     nightmares
    1.14
    Activations Density 0.007%

    No Known Activations