© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 22526
    Prev
    Next
    INDEX
    Explanations

    references to authorities and governing bodies in the context of analysis and decision-making

    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
    1:0.03
    2:0.06
    3:0.20
    4:0.05
    5:0.05
    6:0.04
    7:0.06
    8:0.05
    9:0.04
    10:0.26
    11:0.07
    Negative Logits
    �
    -2.17
    �
    -2.12
    ————
    -2.11
    >>>
    -2.02
    >(
    -1.94
     wondering
    -1.93
     �
    -1.90
    *,
    -1.88
    *.
    -1.87
     Curious
    -1.86
    POSITIVE LOGITS
     lacks
    2.82
     lacked
    2.63
     differed
    2.61
     differs
    2.49
     survives
    2.48
     interfered
    2.45
     exceeds
    2.43
     resembled
    2.40
     survived
    2.35
    anium
    2.34
    Activations Density 0.888%

    No Known Activations