© 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. 2589
    Prev
    Next
    INDEX
    Explanations

    concepts related to ecological and biological systems, particularly in relation to evolution and adaptation

    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
    1:0.05
    2:0.07
    3:0.11
    4:0.18
    5:0.09
    6:0.06
    7:0.13
    8:0.04
    9:0.06
    10:0.04
    11:0.08
    Negative Logits
    Dad
    -2.40
    Fuck
    -2.39
    romeda
    -2.35
     Godd
    -2.31
    fuck
    -2.26
    Tonight
    -2.25
     FUCK
    -2.24
    phabet
    -2.23
    EEEE
    -2.17
    god
    -2.14
    POSITIVE LOGITS
     traditional
    2.68
     Typically
    2.63
     Generally
    2.60
     Often
    2.60
     commonly
    2.51
     typically
    2.50
    Often
    2.49
     exceptions
    2.48
    Typically
    2.39
     Traditional
    2.37
    Activations Density 0.749%

    No Known Activations