© 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. 9-ATT-KK
    11. 6388
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting used within sentences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    3:0.06
    4:0.14
    5:0.07
    6:0.05
    7:0.26
    8:0.07
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
    ────
    -2.32
    addy
    -2.31
    catentry
    -2.29
    books
    -2.28
    etti
    -2.27
     deeds
    -2.25
     perspect
    -2.23
    ascript
    -2.22
     evils
    -2.22
    estate
    -2.17
    POSITIVE LOGITS
     SPEC
    2.67
     Neural
    2.55
    LED
    2.42
     CIS
    2.38
     Juno
    2.37
     STEM
    2.35
     Blackhawks
    2.32
     NCT
    2.31
    <|endoftext|>
    2.31
     Silicon
    2.28
    Activations Density 0.001%

    No Known Activations