© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 35548
    Prev
    Next
    INDEX
    Explanations

    punctuation or sentence boundaries, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.12
    2:0.08
    3:0.06
    4:0.07
    5:0.09
    6:0.07
    7:0.07
    8:0.08
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
     veter
    -2.17
     colle
    -2.09
     arrang
    -2.08
     charact
    -2.06
     carbohyd
    -1.97
     pse
    -1.91
     enthusi
    -1.89
    Magikarp
    -1.87
     weap
    -1.86
     flavours
    -1.84
    POSITIVE LOGITS
     Encounter
    1.97
     Graveyard
    1.89
     Pin
    1.87
     Stadium
    1.87
     Personality
    1.86
     Saturn
    1.77
     Grounds
    1.76
     Mour
    1.73
     Casino
    1.73
     Contact
    1.72
    Activations Density 0.000%

    No Known Activations