© 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. 40643
    Prev
    Next
    INDEX
    Explanations

    numerical data and computer code references

    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
    1:0.02
    2:0.15
    3:0.14
    4:0.14
    5:0.05
    6:0.06
    7:0.06
    8:0.05
    9:0.11
    10:0.09
    11:0.06
    Negative Logits
     eerie
    -1.19
     unprecedented
    -1.19
    idespread
    -1.18
     shockingly
    -1.17
     firsthand
    -1.16
     horrifying
    -1.14
     ominous
    -1.13
    RAG
    -1.12
     cloaked
    -1.11
    razen
    -1.11
    POSITIVE LOGITS
    デ
    1.41
    �
    1.33
    ���
    1.32
    �
    1.32
     Miscellaneous
    1.29
     respectively
    1.25
    作
    1.25
    ricular
    1.24
    senal
    1.22
     nutshell
    1.22
    Activations Density 0.011%

    No Known Activations