© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3656
    Prev
    Next
    INDEX
    Explanations

    statistical data related to health and demographics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.01
    2:0.08
    3:0.20
    4:0.02
    5:0.08
    6:0.02
    7:0.04
    8:0.03
    9:0.01
    10:0.38
    11:0.02
    Negative Logits
    prototype
    -2.31
     simpler
    -2.30
     wiser
    -2.24
    better
    -2.23
     simplified
    -2.14
     easier
    -2.12
     rethink
    -2.12
     quicker
    -2.09
     ));
    -2.09
    ]);
    -2.07
    POSITIVE LOGITS
     anywhere
    2.80
     ratio
    2.74
     Percent
    2.55
     whatsoever
    2.47
     scores
    2.43
     Poverty
    2.38
     Percentage
    2.36
    among
    2.35
     EVER
    2.32
     rates
    2.25
    Activations Density 0.036%

    No Known Activations