© 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. 12841
    Prev
    Next
    INDEX
    Explanations

    phrases and words indicating strong contrasts and transitions

    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
    0:0.08
    1:0.02
    2:0.06
    3:0.12
    4:0.02
    5:0.06
    6:0.02
    7:0.06
    8:0.03
    9:0.01
    10:0.45
    11:0.02
    Negative Logits
     Plans
    -2.26
     Activities
    -2.11
    >)
    -2.00
    heny
    -1.94
    endment
    -1.88
    anything
    -1.85
     Approach
    -1.84
     Rated
    -1.84
     intentions
    -1.83
     destination
    -1.80
    POSITIVE LOGITS
     senseless
    2.32
     into
    2.21
     prematurely
    2.18
    into
    2.18
     awkwardly
    2.13
     painfully
    2.12
     onto
    2.12
     dead
    2.11
     abruptly
    2.11
     unnoticed
    2.08
    Activations Density 0.054%

    No Known Activations