© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43962
    Prev
    Next
    INDEX
    Explanations

    expressions and phrases indicating requests or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.02
    2:0.04
    3:0.07
    4:0.15
    5:0.03
    6:0.05
    7:0.34
    8:0.03
    9:0.04
    10:0.07
    11:0.08
    Negative Logits
     trenches
    -1.76
    ypes
    -1.55
    ��
    -1.55
    vantage
    -1.55
    igree
    -1.52
    ocamp
    -1.51
    vironments
    -1.50
     groove
    -1.49
    kered
    -1.42
    ourney
    -1.42
    POSITIVE LOGITS
     inquiries
    1.92
     allegations
    1.78
     queries
    1.73
     criticism
    1.71
     requests
    1.66
     inaction
    1.66
     petitions
    1.61
     inquiry
    1.58
     baseless
    1.57
     criticisms
    1.55
    Activations Density 0.009%

    No Known Activations