© 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. 8891
    Prev
    Next
    INDEX
    Explanations

    terms related to professional roles and responsibilities, especially in a legal or social context

    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
    1:0.03
    2:0.04
    3:0.17
    4:0.03
    5:0.04
    6:0.02
    7:0.04
    8:0.02
    9:0.02
    10:0.43
    11:0.04
    Negative Logits
     separately
    -2.86
     owing
    -2.30
    Apart
    -2.21
     respectively
    -2.18
     behind
    -2.11
     accordingly
    -2.10
     ahead
    -2.08
     independently
    -2.07
     afterwards
    -2.07
    behind
    -2.02
    POSITIVE LOGITS
     thrive
    2.12
    pmwiki
    1.97
    rouse
    1.87
    unci
    1.87
     acceptable
    1.85
     thri
    1.83
    ECT
    1.80
     tolerate
    1.80
    missible
    1.79
     advertised
    1.79
    Activations Density 0.064%

    No Known Activations