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. 7567
    Prev
    Next
    INDEX
    Explanations

    common words associated with structure and composition

    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
    0:0.07
    1:0.08
    2:0.08
    3:0.09
    4:0.09
    5:0.08
    6:0.09
    7:0.08
    8:0.07
    9:0.09
    10:0.06
    11:0.07
    Negative Logits
     disposable
    -3.30
     untreated
    -3.06
     stranded
    -2.73
     intrusive
    -2.71
     repe
    -2.65
     unaccount
    -2.61
     mobility
    -2.54
     voic
    -2.53
     diseng
    -2.52
     cellul
    -2.52
    POSITIVE LOGITS
     Haf
    3.25
    elsius
    3.06
    �
    2.98
     Jeb
    2.95
     Ahmad
    2.88
     Buk
    2.85
    heit
    2.81
    �
    2.81
     Mathematics
    2.80
     Peng
    2.76
    Activations Density 0.000%

    No Known Activations