© 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. 12468
    Prev
    Next
    INDEX
    Explanations

    concepts related to project development methodologies, specifically focusing on the Minimum Viable Product and proof-of-concept

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

    phrases related to proof-of-concept in technology and innovation

    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
    0:0.01
    1:0.03
    2:0.08
    3:0.24
    4:0.01
    5:0.02
    6:0.07
    7:0.14
    8:0.05
    9:0.09
    10:0.06
    11:0.14
    Negative Logits
    _-
    -1.24
    ゼウス
    -1.22
    too
    -1.19
    ollen
    -1.12
    MSN
    -1.12
    gie
    -1.11
    =-=-=-=-=-=-=-=-
    -1.11
    �
    -1.11
    inates
    -1.10
    ディ
    -1.09
    POSITIVE LOGITS
     quir
    1.16
     exist
    1.12
     equival
    1.11
     evolution
    1.09
     antis
    1.08
     authenticity
    1.07
    lege
    1.04
     existence
    1.01
     viability
    1.01
     polymer
    1.01
    Activations Density 0.009%

    No Known Activations