© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 47272
    Prev
    Next
    INDEX
    Explanations

    copyright notices and associated terms

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.05
    1:0.04
    2:0.09
    3:0.10
    4:0.06
    5:0.05
    6:0.10
    7:0.09
    8:0.04
    9:0.06
    10:0.09
    11:0.18
    Negative Logits
    forest
    -1.48
    spir
    -1.41
    Bloom
    -1.39
    panic
    -1.36
    Sov
    -1.34
    rop
    -1.30
    cause
    -1.30
    urally
    -1.29
    fam
    -1.29
    opia
    -1.27
    POSITIVE LOGITS
    TAG
    1.47
    ��
    1.39
     Pastebin
    1.34
     reprinted
    1.29
    ��
    1.27
     archived
    1.26
     Conan
    1.22
    malink
    1.22
     Cosponsors
    1.22
     Posts
    1.21
    Activations Density 0.002%

    No Known Activations