© 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. 3-ATT-KK
    11. 5585
    Prev
    Next
    INDEX
    Explanations

    punctuation that indicates dialogue or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.06
    2:0.04
    3:0.02
    4:0.05
    5:0.23
    6:0.07
    7:0.02
    8:0.07
    9:0.22
    10:0.08
    11:0.04
    Negative Logits
    bidden
    -1.94
    anwhile
    -1.82
     sidx
    -1.64
    imura
    -1.60
    cknow
    -1.46
    etheless
    -1.41
    icut
    -1.41
    ット
    -1.41
    %);
    -1.40
    ivably
    -1.39
    POSITIVE LOGITS
     myself
    2.27
     my
    2.23
    ..."
    1.95
     majesty
    1.67
    ️
    1.60
    ,''
    1.58
     …"
    1.53
    ..."
    1.51
     I
    1.48
    milo
    1.47
    Activations Density 0.038%

    No Known Activations