© 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. 1298
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and numerical data

    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
    0:0.05
    1:0.12
    2:0.08
    3:0.11
    4:0.08
    5:0.04
    6:0.09
    7:0.13
    8:0.05
    9:0.07
    10:0.11
    11:0.03
    Negative Logits
     exception
    -2.83
     handful
    -2.61
     hindsight
    -2.58
     favourites
    -2.46
     none
    -2.42
     exceptions
    -2.41
    isable
    -2.33
     lone
    -2.29
     certain
    -2.28
     minimal
    -2.25
    POSITIVE LOGITS
    natureconservancy
    2.71
    ACP
    2.63
    >(
    2.62
    olor
    2.57
    jong
    2.53
    ichick
    2.50
    govtrack
    2.43
    ulas
    2.38
    auntlets
    2.38
    opal
    2.38
    Activations Density 0.000%

    No Known Activations