© 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. 9-ATT-KK
    11. 9633
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to identity and diversity, particularly in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.02
    2:0.07
    3:0.46
    4:0.02
    5:0.09
    6:0.02
    7:0.06
    8:0.04
    9:0.02
    10:0.09
    11:0.02
    Negative Logits
     lockout
    -2.16
     consolidation
    -2.16
    staking
    -2.11
    Timeout
    -2.06
     Scotia
    -2.05
    ��極
    -2.04
    yssey
    -2.01
     downgrade
    -1.98
     doubling
    -1.98
     Gamble
    -1.92
    POSITIVE LOGITS
     objects
    3.80
     beings
    3.61
     animals
    3.59
     humans
    3.47
     creatures
    3.34
     NPCs
    3.30
     subjects
    3.28
     strangers
    3.25
     bodies
    3.22
     actors
    3.21
    Activations Density 0.925%

    No Known Activations