© 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. 24186
    Prev
    Next
    INDEX
    Explanations

    statements or inquiries related to changes and impacts

    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
    1:0.34
    2:0.05
    3:0.06
    4:0.17
    5:0.05
    6:0.03
    7:0.06
    8:0.04
    9:0.02
    10:0.03
    11:0.05
    Negative Logits
    ogan
    -2.62
    uana
    -2.60
     indebted
    -2.45
    gered
    -2.45
    illac
    -2.44
    lag
    -2.40
    itton
    -2.35
     substantially
    -2.33
    atics
    -2.32
    ethy
    -2.30
    POSITIVE LOGITS
     How
    4.88
    what
    4.81
    why
    4.76
    Does
    4.75
    How
    4.71
    What
    4.67
     What
    4.64
    Who
    4.64
    how
    4.49
     Does
    4.41
    Activations Density 0.088%

    No Known Activations