© 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. 22511
    Prev
    Next
    INDEX
    Explanations

    discussions about academic publishing and peer review challenges

    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
    0:0.25
    1:0.03
    2:0.13
    3:0.09
    4:0.04
    5:0.09
    6:0.06
    7:0.06
    8:0.08
    9:0.07
    10:0.04
    11:0.02
    Negative Logits
    Battery
    -2.67
    ��
    -2.67
     awoken
    -2.65
     Poke
    -2.59
    Pokemon
    -2.56
     GoPro
    -2.55
     Macy
    -2.54
    Gy
    -2.49
     mall
    -2.48
    twitch
    -2.44
    POSITIVE LOGITS
     journals
    5.04
     manuscripts
    4.74
    TeX
    4.66
     Journals
    4.59
    authors
    4.53
     Authors
    4.49
     publication
    4.48
     journal
    4.47
     manuscript
    4.40
     publish
    4.37
    Activations Density 0.083%

    No Known Activations