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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43602
    Prev
    Next
    INDEX
    Explanations

    occurrences of proper nouns and significant names

    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
    0:0.06
    1:0.51
    2:0.03
    3:0.03
    4:0.02
    5:0.11
    6:0.03
    7:0.02
    8:0.03
    9:0.04
    10:0.03
    11:0.03
    Negative Logits
    aura
    -2.46
    atem
    -2.14
    amber
    -2.05
    roma
    -2.03
    cius
    -1.99
    cham
    -1.99
    amera
    -1.96
    awn
    -1.95
    ummies
    -1.94
    auldron
    -1.90
    POSITIVE LOGITS
    Fs
    2.43
     Fas
    2.21
     Fin
    2.05
     Falk
    2.04
     F
    2.01
    F
    2.00
     Fitzgerald
    1.97
     Fior
    1.94
     Adin
    1.89
    fuck
    1.86
    Activations Density 0.070%

    No Known Activations