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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 44299
    Prev
    Next
    INDEX
    Explanations

    specific symbols or characters that may indicate formatting or transcription errors

    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
    2:0.07
    3:0.08
    4:0.07
    5:0.04
    6:0.21
    7:0.04
    8:0.11
    9:0.08
    10:0.12
    11:0.08
    Negative Logits
     Poc
    -1.42
     Cly
    -1.39
     Cyp
    -1.30
     Marriott
    -1.30
     Speedway
    -1.29
     Sparks
    -1.29
     cataly
    -1.28
     Kinder
    -1.28
     Vog
    -1.26
     Plat
    -1.22
    POSITIVE LOGITS
    enter
    1.50
    ネ
    1.40
    translation
    1.39
    olon
    1.38
    archives
    1.37
    Reviewed
    1.36
    oidal
    1.36
    Introduced
    1.35
    livion
    1.34
    elo
    1.33
    Activations Density 0.003%

    No Known Activations