© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 8215
    Prev
    Next
    INDEX
    Explanations

    phrases related to body measurements and physical attributes

    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
    1:0.02
    2:0.09
    3:0.32
    4:0.01
    5:0.02
    6:0.13
    7:0.07
    8:0.03
    9:0.04
    10:0.05
    11:0.15
    Negative Logits
     propensity
    -1.31
     disadvant
    -1.31
     inconsistency
    -1.26
    anan
    -1.14
    utical
    -1.13
    zai
    -1.13
    ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ
    -1.11
     Maher
    -1.11
     polarization
    -1.11
     Haku
    -1.11
    POSITIVE LOGITS
    Initialized
    1.46
    heartedly
    1.34
    empt
    1.33
    hearted
    1.29
    circ
    1.27
    });
    1.23
    pection
    1.23
    ilts
    1.23
    fledged
    1.21
    empty
    1.18
    Activations Density 0.039%

    No Known Activations