© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 16335
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and connectors in sentences

    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
    2:0.07
    3:0.03
    4:0.06
    5:0.03
    6:0.20
    7:0.05
    8:0.06
    9:0.29
    10:0.02
    11:0.06
    Negative Logits
     Lug
    -3.99
     locom
    -3.63
    automatic
    -3.52
    alias
    -3.48
    alogue
    -3.44
     sulph
    -3.41
     Yang
    -3.25
     Lung
    -3.23
     aliases
    -3.23
    Yang
    -3.22
    POSITIVE LOGITS
     Perkins
    11.91
     Perry
    5.27
     Parker
    5.20
    Per
    4.61
     Harris
    4.46
    Harris
    4.45
     Ellison
    4.40
     Perez
    4.38
     Percy
    4.21
     Olson
    4.16
    Activations Density 0.001%

    No Known Activations