© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14756
    Prev
    Next
    INDEX
    Explanations

    structural elements or markers in the text, such as brackets or punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.23
    2:0.08
    3:0.09
    4:0.06
    5:0.03
    6:0.10
    7:0.06
    8:0.03
    9:0.04
    10:0.05
    11:0.08
    Negative Logits
    Si
    -3.14
     Mour
    -2.96
     Machines
    -2.77
    ô
    -2.62
    Reviewer
    -2.60
    Johnson
    -2.56
    separ
    -2.52
     Popular
    -2.52
    cho
    -2.49
     JO
    -2.48
    POSITIVE LOGITS
     baseline
    5.72
     Unch
    3.80
    base
    3.56
    elines
    3.43
     normalized
    3.42
     peanuts
    3.08
     STAND
    2.94
    bas
    2.92
    ummies
    2.85
     base
    2.82
    Activations Density 0.000%

    No Known Activations