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. 2-ATT-KK
    6. 13976
    Prev
    Next
    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.02
    2:0.12
    3:0.07
    4:0.04
    5:0.09
    6:0.06
    7:0.10
    8:0.04
    9:0.04
    10:0.19
    11:0.10
    Negative Logits
    $$$$
    -0.86
    SPONSORED
    -0.77
    LD
    -0.76
    mA
    -0.69
    inav
    -0.68
    umbn
    -0.67
    mx
    -0.67
    $$
    -0.67
     envelope
    -0.66
    mitt
    -0.66
    POSITIVE LOGITS
    FIELD
    0.92
    ":[{"
    0.91
     Conclusion
    0.88
     Lumpur
    0.85
     Appeal
    0.82
     Peninsula
    0.78
    enei
    0.77
    etooth
    0.77
    udos
    0.75
    clair
    0.75
    Activations Density 0.256%

    No Known Activations