© 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. 5-ATT-KK
    11. 45693
    Prev
    Next
    INDEX
    Explanations

    abbreviations related to organizations and commissions

    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
    0:0.06
    1:0.11
    2:0.03
    3:0.03
    4:0.03
    5:0.37
    6:0.03
    7:0.02
    8:0.03
    9:0.07
    10:0.14
    11:0.03
    Negative Logits
    �
    -1.89
     cous
    -1.78
    �
    -1.65
     cher
    -1.60
    ;;;;;;;;;;;;
    -1.54
    о�
    -1.54
     �
    -1.53
     afore
    -1.53
     remem
    -1.52
    黒
    -1.51
    POSITIVE LOGITS
     Adin
    1.73
    developed
    1.68
    issions
    1.63
     centralized
    1.58
    orough
    1.57
    ropolis
    1.56
    arch
    1.50
     Cause
    1.45
    Features
    1.45
    HQ
    1.45
    Activations Density 0.016%

    No Known Activations