© 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. 22640
    Prev
    Next
    INDEX
    Explanations

    details and supporting information related to a specific topic or narrative

    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
    0:0.06
    1:0.02
    2:0.05
    3:0.20
    4:0.04
    5:0.09
    6:0.03
    7:0.07
    8:0.03
    9:0.02
    10:0.31
    11:0.03
    Negative Logits
    pires
    -2.39
    atism
    -1.86
     chronically
    -1.78
     offend
    -1.76
     depended
    -1.75
    increasing
    -1.70
     vain
    -1.68
     balk
    -1.67
     lacked
    -1.65
     feared
    -1.65
    POSITIVE LOGITS
     details
    3.24
     overview
    3.21
     particulars
    2.95
     rundown
    2.88
     pertinent
    2.82
     explanation
    2.77
     synopsis
    2.77
     description
    2.76
     info
    2.73
     detailed
    2.72
    Activations Density 0.410%

    No Known Activations