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. 9-ATT-KK
    6. 7640
    Prev
    Next
    INDEX
    Explanations

    the word "down."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.06
    2:0.07
    3:0.08
    4:0.08
    5:0.08
    6:0.09
    7:0.07
    8:0.09
    9:0.09
    10:0.07
    11:0.09
    Negative Logits
     Browse
    -2.89
    ortment
    -2.54
     TAMADRA
    -2.53
    kes
    -2.49
    �
    -2.47
    rez
    -2.46
    zens
    -2.42
    ECK
    -2.42
    †
    -2.40
    ez
    -2.37
    POSITIVE LOGITS
     carriage
    3.67
     monopol
    2.93
     Boko
    2.87
     Birmingham
    2.74
     negro
    2.71
     Jamaica
    2.71
     pastors
    2.69
     Camel
    2.69
     camel
    2.69
     Liberia
    2.68
    Activations Density 0.000%

    No Known Activations