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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7731
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and individual identities

    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
    0:0.08
    1:0.04
    2:0.04
    3:0.02
    4:0.11
    5:0.37
    6:0.05
    7:0.05
    8:0.03
    9:0.03
    10:0.09
    11:0.03
    Negative Logits
     opponents
    -1.82
    genre
    -1.81
     penetrating
    -1.78
     foes
    -1.74
     sheer
    -1.73
     deflect
    -1.66
     predictive
    -1.65
    players
    -1.61
     adversaries
    -1.59
     thickness
    -1.55
    POSITIVE LOGITS
    amily
    2.24
     Donation
    2.18
     PsyNet
    2.04
    married
    2.01
    accompan
    1.99
     contrace
    1.84
     Married
    1.83
     grandson
    1.80
     paternity
    1.78
     gardening
    1.76
    Activations Density 0.231%

    No Known Activations