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. 10616
    Prev
    Next
    INDEX
    Explanations

    specific terms related to botany and botanical classifications

    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
    0:0.03
    1:0.03
    2:0.03
    3:0.04
    4:0.05
    5:0.05
    6:0.03
    7:0.05
    8:0.52
    9:0.03
    10:0.03
    11:0.06
    Negative Logits
    BuyableInstoreAndOnline
    -2.53
    Obama
    -2.35
    Romney
    -2.29
    Republican
    -2.27
    acted
    -2.23
    Sher
    -2.19
    Jews
    -2.12
    Clinton
    -2.05
    partisan
    -1.98
    interstitial
    -1.93
    POSITIVE LOGITS
     Intermediate
    2.44
     Features
    2.29
     Availability
    2.28
     Owner
    2.22
     Tools
    2.19
     Bits
    2.19
     Invalid
    2.12
     Macro
    2.10
     Label
    2.10
     Starting
    2.09
    Activations Density 0.356%

    No Known Activations