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. 7682
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific letter or character

    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
    0:0.06
    1:0.08
    2:0.08
    3:0.09
    4:0.08
    5:0.08
    6:0.09
    7:0.08
    8:0.07
    9:0.08
    10:0.07
    11:0.09
    Negative Logits
    assment
    -2.88
    .</
    -2.80
     =====
    -2.68
     ~/
    -2.68
     XD
    -2.67
    /-
    -2.63
    )</
    -2.62
     prosec
    -2.61
    successfully
    -2.59
    hao
    -2.58
    POSITIVE LOGITS
     Balkans
    3.29
     Africans
    2.96
     Ethiopia
    2.94
     historian
    2.88
     Somalia
    2.69
     Yugoslavia
    2.68
    BBC
    2.66
     bear
    2.58
     Africa
    2.58
     bears
    2.55
    Activations Density 0.000%

    No Known Activations