Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3173
    Prev
    Next
    INDEX
    Explanations

    the conjunction "or."

    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
    1:0.09
    2:0.07
    3:0.09
    4:0.08
    5:0.07
    6:0.06
    7:0.09
    8:0.07
    9:0.09
    10:0.07
    11:0.08
    Negative Logits
    iOS
    -2.95
    berus
    -2.90
    anke
    -2.88
    tile
    -2.82
    ilage
    -2.75
    orea
    -2.70
    ichick
    -2.61
    Poké
    -2.61
    icut
    -2.58
    football
    -2.57
    POSITIVE LOGITS
     relational
    2.82
     Distribut
    2.75
     Volunteer
    2.75
     supporting
    2.64
     Relations
    2.61
     Conver
    2.58
     feminist
    2.56
     constituent
    2.56
     Contribut
    2.54
     Supporting
    2.48
    Activations Density 0.000%

    No Known Activations