© 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. 37876
    Prev
    Next
    INDEX
    Explanations

    distinct categories or labels represented by tags

    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
    0:0.03
    1:0.04
    2:0.08
    3:0.12
    4:0.10
    5:0.06
    6:0.09
    7:0.03
    8:0.06
    9:0.13
    10:0.09
    11:0.13
    Negative Logits
    anye
    -1.18
     Chero
    -1.17
     Clarkson
    -1.13
     tweets
    -1.11
     Mercer
    -1.06
     Wolves
    -1.05
     Grande
    -1.04
     apost
    -1.03
     Rebels
    -1.03
     Apost
    -1.02
    POSITIVE LOGITS
    akening
    1.20
    doi
    1.13
    ccording
    1.10
    0010
    1.07
     fuzz
    1.06
    Introduction
    1.03
    Physical
    1.02
    iquid
    1.02
     Solution
    1.02
     compromise
    1.01
    Activations Density 0.091%

    No Known Activations