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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43202
    Prev
    Next
    INDEX
    Explanations

    percentages and comparisons in data-driven contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.01
    2:0.16
    3:0.29
    4:0.08
    5:0.05
    6:0.03
    7:0.03
    8:0.04
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
     flyers
    -1.46
     Phi
    -1.40
     Marse
    -1.36
     Fle
    -1.35
     Laf
    -1.35
     Haas
    -1.35
     Esper
    -1.32
     Kling
    -1.31
     Apostle
    -1.28
     incorpor
    -1.27
    POSITIVE LOGITS
    ']
    2.13
    ?]
    2.06
    ?」
    2.03
    ?'
    1.91
    /(
    1.86
    malink
    1.82
    ').
    1.80
    "]
    1.77
    '?
    1.72
    >)
    1.66
    Activations Density 0.007%

    No Known Activations