© 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. 16934
    Prev
    Next
    INDEX
    Explanations

    references to organizations, programs, and structured entities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.02
    1:0.01
    2:0.22
    3:0.18
    4:0.18
    5:0.04
    6:0.04
    7:0.03
    8:0.04
    9:0.09
    10:0.06
    11:0.04
    Negative Logits
     Ferr
    -1.44
    etically
    -1.38
    anish
    -1.38
    astical
    -1.38
    kas
    -1.37
     IMAGES
    -1.35
    itably
    -1.29
    phia
    -1.28
    astically
    -1.26
     [*
    -1.26
    POSITIVE LOGITS
    ':
    1.63
    ');
    1.58
    ').
    1.52
    ":
    1.49
    "!
    1.41
    ';
    1.39
    /,
    1.38
    "]=>
    1.37
    ウス
    1.37
     chars
    1.34
    Activations Density 0.012%

    No Known Activations