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. 10600
    Prev
    Next
    INDEX
    Explanations

    words related to human rights and ethical 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
    0:0.01
    1:0.03
    2:0.08
    3:0.11
    4:0.02
    5:0.02
    6:0.15
    7:0.18
    8:0.04
    9:0.06
    10:0.07
    11:0.16
    Negative Logits
    �
    -1.65
    lag
    -1.55
    ickr
    -1.43
    adelphia
    -1.33
    chat
    -1.33
    aucuses
    -1.31
     Lumpur
    -1.31
    iversary
    -1.30
    abad
    -1.29
    ashtra
    -1.25
    POSITIVE LOGITS
    etheless
    1.70
    versions
    1.58
    iencies
    1.29
    enance
    1.25
    ク
    1.24
     Template
    1.20
     Illum
    1.16
    ibly
    1.14
    itably
    1.14
    necessary
    1.12
    Activations Density 0.032%

    No Known Activations