Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 85
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    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
    0:0.07
    1:0.03
    2:0.04
    3:0.04
    4:0.05
    5:0.04
    6:0.19
    7:0.03
    8:0.05
    9:0.35
    10:0.03
    11:0.03
    Negative Logits
     Gupta
    -4.09
    ンジ
    -3.72
    amsung
    -3.53
    dp
    -3.48
    Grid
    -3.47
    1007
    -3.45
     GN
    -3.41
    Pocket
    -3.35
    生
    -3.33
    grid
    -3.33
    POSITIVE LOGITS
     Ale
    8.78
    Ale
    8.51
     ale
    7.77
     ALE
    7.16
     Ole
    5.47
     Alec
    5.12
    ale
    4.26
     Beer
    4.25
     Bere
    4.17
     AE
    4.08
    Activations Density 0.000%

    No Known Activations