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. 5-ATT-KK
    6. 19179
    Prev
    Next
    INDEX
    Explanations

    references to specific time intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.08
    4:0.09
    5:0.08
    6:0.07
    7:0.08
    8:0.09
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    ��
    -1.74
     Reboot
    -1.70
     Tomorrow
    -1.56
     SetFontSize
    -1.50
     guiActiveUnfocused
    -1.48
    uesday
    -1.48
     Rabbi
    -1.47
     Unch
    -1.46
     breakout
    -1.41
     Alz
    -1.41
    POSITIVE LOGITS
    Fram
    1.84
     artif
    1.74
     tricks
    1.66
     allowances
    1.53
     intentions
    1.52
    glomer
    1.49
     shortcuts
    1.49
    anthrop
    1.48
    phia
    1.47
    avascript
    1.47
    Activations Density 0.000%

    No Known Activations