© 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. 10-ATT-KK
    11. 21241
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of lens attachments and cost considerations associated with products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.19
    2:0.09
    3:0.04
    4:0.06
    5:0.02
    6:0.11
    7:0.12
    8:0.02
    9:0.05
    10:0.08
    11:0.08
    Negative Logits
     Weiss
    -3.09
     Ernst
    -2.71
    Weiss
    -2.68
     Dunn
    -2.63
     Rouhani
    -2.62
    ín
    -2.50
    ahan
    -2.50
    ewater
    -2.49
    ahs
    -2.46
     Garc
    -2.43
    POSITIVE LOGITS
     attachment
    5.83
     attachments
    5.30
     attach
    5.13
     attached
    4.98
    attach
    4.60
     attaching
    4.37
    Attach
    4.07
     attaches
    4.00
     detach
    3.70
     cling
    3.54
    Activations Density 0.002%

    No Known Activations