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. 10259
    Prev
    Next
    INDEX
    Explanations

    topics related to regulations and governance issues

    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
    0:0.02
    1:0.03
    2:0.08
    3:0.07
    4:0.03
    5:0.04
    6:0.08
    7:0.40
    8:0.08
    9:0.02
    10:0.05
    11:0.03
    Negative Logits
     reciprocal
    -1.28
     dividend
    -1.28
     penalty
    -1.25
     pigeon
    -1.25
     pleas
    -1.24
     normalized
    -1.22
    xual
    -1.20
     exchanged
    -1.19
     representation
    -1.18
     compensation
    -1.18
    POSITIVE LOGITS
    ć
    1.75
    soDeliveryDate
    1.73
    ondo
    1.55
    ón
    1.48
     Lines
    1.47
    onz
    1.43
    izz
    1.37
    �
    1.34
     Manga
    1.29
    icion
    1.29
    Activations Density 0.200%

    No Known Activations