© 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. 3-ATT-KK
    11. 13042
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to experiments, research, and measurements

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

    phrases related to standards, regulations, and societal expectations

    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
    1:0.04
    2:0.09
    3:0.07
    4:0.01
    5:0.05
    6:0.08
    7:0.22
    8:0.12
    9:0.12
    10:0.07
    11:0.05
    Negative Logits
    agall
    -1.38
    itched
    -1.24
    nown
    -1.22
    atism
    -1.20
    chin
    -1.20
    cock
    -1.19
    ibur
    -1.15
    tnc
    -1.11
    oxicity
    -1.11
    ascript
    -1.07
    POSITIVE LOGITS
     newsp
    1.28
     baskets
    1.20
     manner
    1.16
     Krug
    1.09
     respective
    1.08
     minim
    1.08
     ILCS
    1.04
     IMAGES
    1.02
     mesh
    1.00
     illum
    1.00
    Activations Density 0.188%

    No Known Activations