© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-ATT-KK
    11. 44127
    Prev
    Next
    INDEX
    Explanations

    terms related to programming languages and their libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.04
    2:0.13
    3:0.06
    4:0.05
    5:0.06
    6:0.07
    7:0.04
    8:0.07
    9:0.09
    10:0.10
    11:0.13
    Negative Logits
    esson
    -1.31
     pity
    -1.28
    "]=>
    -1.20
     assum
    -1.19
     mete
    -1.18
    gered
    -1.14
    axter
    -1.11
    MpServer
    -1.11
     Defenders
    -1.10
    rely
    -1.10
    POSITIVE LOGITS
    Material
    1.31
    VW
    1.30
    Enable
    1.25
    Port
    1.24
    Race
    1.20
     Tos
    1.20
    Application
    1.19
    Policy
    1.18
    ISM
    1.16
    Password
    1.16
    Activations Density 0.001%

    No Known Activations