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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18874
    Prev
    Next
    INDEX
    Explanations

    references to measurement units and numerical data

    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
    0:0.02
    1:0.42
    2:0.03
    3:0.04
    4:0.03
    5:0.07
    6:0.09
    7:0.04
    8:0.03
    9:0.10
    10:0.03
    11:0.04
    Negative Logits
     Stephenson
    -3.30
     2024
    -3.00
     Stevenson
    -2.86
     laun
    -2.52
     2019
    -2.51
     Berk
    -2.50
     Fn
    -2.49
    iage
    -2.49
     Asc
    -2.46
    etta
    -2.36
    POSITIVE LOGITS
    ueless
    2.77
    eded
    2.76
    eph
    2.65
    iasis
    2.63
    ewater
    2.63
    ��
    2.61
    urated
    2.59
    orer
    2.56
    eness
    2.55
    irms
    2.50
    Activations Density 0.007%

    No Known Activations