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. 7676
    Prev
    Next
    INDEX
    Explanations

    references to roads, streets, and pathways

    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
    0:0.31
    1:0.03
    2:0.04
    3:0.04
    4:0.06
    5:0.04
    6:0.08
    7:0.09
    8:0.03
    9:0.06
    10:0.11
    11:0.05
    Negative Logits
    itatively
    -1.34
    ifer
    -1.29
    rics
    -1.27
    rating
    -1.27
    insk
    -1.22
    iary
    -1.21
    ollah
    -1.20
    echo
    -1.18
    orate
    -1.18
    lihood
    -1.18
    POSITIVE LOGITS
    ways
    1.52
     travers
    1.38
    side
    1.38
     passage
    1.26
    course
    1.21
     blocked
    1.18
     trave
    1.17
     permitting
    1.15
     sidewalks
    1.15
     unprotected
    1.14
    Activations Density 0.040%

    No Known Activations