© 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. 7395
    Prev
    Next
    INDEX
    Explanations

    references to significant cultural or societal changes

    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
    0:0.03
    1:0.05
    2:0.05
    3:0.07
    4:0.23
    5:0.07
    6:0.04
    7:0.20
    8:0.05
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
     Metatron
    -2.61
    yip
    -2.58
     him
    -2.53
    itates
    -2.23
    rade
    -2.23
    cheat
    -2.21
    yo
    -2.19
     understands
    -2.18
    ibo
    -2.15
    plet
    -2.14
    POSITIVE LOGITS
    was
    4.04
    Eventually
    3.58
     consisted
    3.55
    later
    3.49
     remained
    3.49
    had
    3.41
    were
    3.40
     mattered
    3.39
     culminated
    3.22
     became
    3.13
    Activations Density 1.566%

    No Known Activations