© 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. 20378
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a case-by-case basis approach

    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
    1:0.15
    2:0.03
    3:0.14
    4:0.03
    5:0.08
    6:0.11
    7:0.04
    8:0.03
    9:0.23
    10:0.03
    11:0.07
    Negative Logits
    Rh
    -2.88
     Staten
    -2.77
     Nikki
    -2.66
    wr
    -2.63
     navig
    -2.59
     Rhode
    -2.58
     Eleven
    -2.54
    nin
    -2.52
     REL
    -2.50
     Rodrig
    -2.49
    POSITIVE LOGITS
    Case
    3.42
     CASE
    3.23
    case
    3.00
     Case
    2.76
     Casey
    2.67
    avis
    2.61
     case
    2.58
     Cases
    2.57
    cases
    2.55
    aq
    2.50
    Activations Density 0.001%

    No Known Activations