© 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. 12868
    Prev
    Next
    INDEX
    Explanations

    statements about significance and value

    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
    1:0.05
    2:0.08
    3:0.09
    4:0.03
    5:0.05
    6:0.03
    7:0.29
    8:0.03
    9:0.05
    10:0.12
    11:0.08
    Negative Logits
     separately
    -2.62
    udging
    -2.48
     afterward
    -2.45
     cautioned
    -2.39
     skeptical
    -2.39
    secondary
    -2.36
     Sullivan
    -2.26
     skepticism
    -2.24
     later
    -2.24
     congressional
    -2.23
    POSITIVE LOGITS
    �
    3.01
    サ
    2.70
    amac
    2.56
    \\
    2.29
    ////
    2.23
     fucking
    2.19
    bred
    2.18
     effortlessly
    2.17
     ILCS
    2.15
    9999
    2.13
    Activations Density 0.003%

    No Known Activations