© 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. 12855
    Prev
    Next
    INDEX
    Explanations

    code snippets related to manipulating paths in URLs

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

    programming loops and control structures in code

    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
    1:0.08
    2:0.07
    3:0.04
    4:0.07
    5:0.08
    6:0.07
    7:0.06
    8:0.05
    9:0.22
    10:0.07
    11:0.09
    Negative Logits
     Skinner
    -1.25
     fundament
    -1.22
     hinges
    -1.16
    う
    -1.14
     principle
    -1.13
     awa
    -1.11
    OTE
    -1.11
     regulator
    -1.10
     sentient
    -1.09
     criminality
    -1.09
    POSITIVE LOGITS
    ullivan
    1.55
    oglu
    1.54
    lehem
    1.43
    wic
    1.41
    quart
    1.39
    anwhile
    1.35
    ulia
    1.34
    =(
    1.34
    llor
    1.32
    icipated
    1.31
    Activations Density 0.014%

    No Known Activations