© 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. 21257
    Prev
    Next
    INDEX
    Explanations

    instances where access or entry is being restricted or denied

    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
    0:0.21
    1:0.10
    2:0.09
    3:0.07
    4:0.04
    5:0.02
    6:0.09
    7:0.09
    8:0.02
    9:0.05
    10:0.11
    11:0.04
    Negative Logits
     Jindal
    -3.36
    Vel
    -3.29
     TAG
    -3.18
     Tunis
    -3.13
    ι
    -3.09
     CMS
    -3.08
     Libya
    -3.01
     Athe
    -2.98
    Lat
    -2.98
     DOM
    -2.93
    POSITIVE LOGITS
     Stanley
    9.74
    Stan
    6.63
     Kubrick
    5.67
     Stan
    5.48
     Blackhawks
    4.78
     Calder
    4.19
     hockey
    4.11
     Crosby
    3.92
     Penguins
    3.90
     Norris
    3.86
    Activations Density 0.004%

    No Known Activations