© 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. 10-ATT-KK
    11. 22790
    Prev
    Next
    INDEX
    Explanations

    references to organizations, particularly nonprofits and groups involved in research or advocacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.03
    3:0.06
    4:0.12
    5:0.23
    6:0.02
    7:0.08
    8:0.02
    9:0.30
    10:0.02
    11:0.04
    Negative Logits
     hindsight
    -2.53
     Seconds
    -2.42
     enough
    -2.36
    Something
    -2.30
     Subtle
    -2.29
    estamp
    -2.25
     anyway
    -2.24
    akings
    -2.22
    instead
    -2.15
     EVEN
    -2.14
    POSITIVE LOGITS
    quartered
    2.93
     headquartered
    2.81
     financed
    2.76
     specializing
    2.67
     staffed
    2.61
     collabor
    2.60
     devoted
    2.58
     dedicated
    2.50
     distributed
    2.50
     marketed
    2.48
    Activations Density 0.060%

    No Known Activations