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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2999
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or names

    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
    0:0.10
    1:0.09
    2:0.04
    3:0.03
    4:0.03
    5:0.27
    6:0.04
    7:0.01
    8:0.04
    9:0.14
    10:0.12
    11:0.04
    Negative Logits
    nance
    -1.56
    notation
    -1.53
    DAQ
    -1.41
    aic
    -1.40
    ��
    -1.35
    oms
    -1.34
    ournal
    -1.31
    cn
    -1.31
    jl
    -1.27
    �
    -1.23
    POSITIVE LOGITS
    enegger
    1.68
    's
    1.61
     himself
    1.54
     reluctantly
    1.47
     angrily
    1.45
     shaved
    1.44
     enrolled
    1.43
     enjoys
    1.43
     verbally
    1.42
     divorced
    1.41
    Activations Density 0.174%

    No Known Activations