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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 7702
    Prev
    Next
    INDEX
    Explanations

    relationships and comparisons involving biological or systemic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.08
    3:0.07
    4:0.03
    5:0.03
    6:0.12
    7:0.39
    8:0.07
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
    \<
    -1.19
    pmwiki
    -1.17
     Flavoring
    -1.16
     Annotations
    -1.16
    ealous
    -1.12
     Vaugh
    -1.06
    rities
    -1.06
     Voices
    -1.05
    ebook
    -1.04
    ittees
    -1.03
    POSITIVE LOGITS
    xual
    1.24
    si
    1.24
    ue
    1.21
    TPPStreamerBot
    1.18
    ult
    1.17
    urat
    1.13
    EStream
    1.13
    dan
    1.13
    rol
    1.13
    assic
    1.13
    Activations Density 0.253%

    No Known Activations