© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9587
    Prev
    Next
    INDEX
    Explanations

    indicators of specific structured information or references

    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
    0:0.03
    1:0.10
    2:0.03
    3:0.05
    4:0.02
    5:0.03
    6:0.05
    7:0.03
    8:0.02
    9:0.54
    10:0.03
    11:0.02
    Negative Logits
    erk
    -3.68
    elo
    -3.67
     Tes
    -3.63
     Joel
    -3.46
    PLIC
    -3.45
    ela
    -3.42
    Tes
    -3.39
    ula
    -3.34
     Bree
    -3.33
     Bolt
    -3.31
    POSITIVE LOGITS
    11
    5.59
     11
    5.30
    2011
    4.66
    111
    4.48
     2011
    4.24
     eleven
    4.12
    raph
    4.09
     111
    4.08
    1111
    3.78
    011
    3.78
    Activations Density 0.036%

    No Known Activations