© 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. 13734
    Prev
    Next
    INDEX
    Explanations

    file paths or directories

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

    technical terms and instructions related to software development and system configurations

    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
    0:0.05
    1:0.06
    2:0.11
    3:0.08
    4:0.04
    5:0.08
    6:0.08
    7:0.08
    8:0.14
    9:0.07
    10:0.09
    11:0.07
    Negative Logits
    awed
    -1.41
    arians
    -1.39
    apego
    -1.35
    atism
    -1.23
    ocious
    -1.22
    olit
    -1.20
     drugs
    -1.19
    aughs
    -1.15
    antz
    -1.15
     bruises
    -1.15
    POSITIVE LOGITS
     context
    1.76
     Settings
    1.71
     directory
    1.62
     namespace
    1.62
     folder
    1.55
     settings
    1.54
     format
    1.50
     configuration
    1.49
     vicinity
    1.47
     mode
    1.47
    Activations Density 0.096%

    No Known Activations