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. 7-ATT-KK
    6. 8935
    Prev
    Next
    INDEX
    Explanations

    references to user interactions and role management in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.37
    1:0.07
    2:0.05
    3:0.05
    4:0.05
    5:0.04
    6:0.06
    7:0.04
    8:0.05
    9:0.08
    10:0.05
    11:0.04
    Negative Logits
     negatives
    -1.83
     cursing
    -1.70
     blues
    -1.68
     inhib
    -1.67
     hurts
    -1.61
     singers
    -1.59
     spoilers
    -1.56
     blacks
    -1.56
     positives
    -1.55
     Africans
    -1.55
    POSITIVE LOGITS
    ^{
    2.14
    ��
    1.87
    Const
    1.85
    Toy
    1.84
    ython
    1.84
    �
    1.81
    Documents
    1.76
    �
    1.74
    arser
    1.73
    _{
    1.72
    Activations Density 0.015%

    No Known Activations