© 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. 9-ATT-KK
    11. 7471
    Prev
    Next
    INDEX
    Explanations

    occurrences of letters and symbols, likely related to formatting or referencing in text

    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
    0:0.04
    1:0.03
    2:0.03
    3:0.14
    4:0.03
    5:0.13
    6:0.04
    7:0.04
    8:0.03
    9:0.03
    10:0.04
    11:0.36
    Negative Logits
     ):
    -2.76
    ↵ 
    -2.40
     );
    -2.35
    !".
    -2.28
    Joined
    -2.25
     chars
    -2.19
     Cause
    -2.17
     "…
    -2.14
     tremend
    -2.13
     Spend
    -2.11
    POSITIVE LOGITS
    .
    3.12
    ellen
    2.97
    iola
    2.69
    ajor
    2.69
    .-
    2.65
    ._
    2.57
    arily
    2.56
    .>>
    2.54
    eredith
    2.54
    ��
    2.53
    Activations Density 0.009%

    No Known Activations