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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8599
    Prev
    Next
    INDEX
    Explanations

    concepts related to autonomy and rights

    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
    0:0.03
    1:0.06
    2:0.12
    3:0.05
    4:0.03
    5:0.06
    6:0.08
    7:0.09
    8:0.17
    9:0.09
    10:0.08
    11:0.08
    Negative Logits
    emonium
    -1.22
     fielded
    -1.12
     curve
    -1.08
    BuyableInstoreAndOnline
    -1.08
     eruption
    -1.06
     suggesting
    -1.06
     underest
    -1.04
     skew
    -1.04
     primed
    -1.02
    tick
    -1.01
    POSITIVE LOGITS
    equality
    1.27
    ordable
    1.18
    rones
    1.17
    thood
    1.16
    ヘ
    1.16
     SetFontSize
    1.15
    ック
    1.15
    omever
    1.15
     lawfully
    1.14
     Rights
    1.13
    Activations Density 0.034%

    No Known Activations