© 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. 15347
    Prev
    Next
    INDEX
    Explanations

    aspects related to financial costs and comparisons

    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
    0:0.09
    1:0.02
    2:0.06
    3:0.05
    4:0.04
    5:0.04
    6:0.14
    7:0.05
    8:0.21
    9:0.17
    10:0.03
    11:0.02
    Negative Logits
    estern
    -4.10
     viol
    -3.81
     Schwar
    -3.76
     canyon
    -3.52
     Zion
    -3.51
     Rav
    -3.36
     violin
    -3.35
     contrace
    -3.34
     resil
    -3.34
     Hin
    -3.34
    POSITIVE LOGITS
     Newcastle
    10.39
    castle
    5.90
    ynes
    4.63
     NRL
    4.54
     McA
    4.44
     MacDonald
    4.44
     Faw
    4.42
     Ferry
    4.33
     Smy
    4.26
     Sydney
    4.25
    Activations Density 0.002%

    No Known Activations