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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 8068
    Prev
    Next
    INDEX
    Explanations

    references to digital platforms and their functionalities

    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
    0:0.04
    1:0.04
    2:0.03
    3:0.14
    4:0.05
    5:0.05
    6:0.03
    7:0.08
    8:0.04
    9:0.03
    10:0.11
    11:0.29
    Negative Logits
     ''
    -2.19
     amounted
    -2.14
     "'
    -2.12
    hement
    -1.97
     "(
    -1.95
    ecause
    -1.88
    ificantly
    -1.86
     ((
    -1.84
    elled
    -1.82
     '
    -1.81
    POSITIVE LOGITS
    !,
    3.34
    ?,
    3.30
    ,...
    3.29
    /,
    2.97
    [/
    2.63
     Citation
    2.61
    ,[
    2.59
    +,
    2.44
    ®,
    2.35
    ,
    2.35
    Activations Density 0.024%

    No Known Activations