© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10180
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific numerical values or measurements

    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
    1:0.45
    2:0.04
    3:0.06
    4:0.05
    5:0.04
    6:0.04
    7:0.06
    8:0.03
    9:0.09
    10:0.03
    11:0.02
    Negative Logits
     ILCS
    -2.39
    catentry
    -2.31
    joice
    -2.27
     rall
    -2.26
    othe
    -2.21
    shr
    -2.20
    closure
    -2.20
    sth
    -2.18
     nevertheless
    -2.15
     guid
    -2.13
    POSITIVE LOGITS
     two
    5.58
    two
    5.40
    three
    5.34
     three
    5.18
    Two
    4.95
     TWO
    4.83
     THREE
    4.82
    Three
    4.63
     Two
    4.33
     Three
    4.18
    Activations Density 0.068%

    No Known Activations