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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 44314
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting variations in text

    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
    0:0.09
    1:0.03
    2:0.09
    3:0.07
    4:0.06
    5:0.07
    6:0.03
    7:0.04
    8:0.21
    9:0.12
    10:0.06
    11:0.09
    Negative Logits
    soType
    -1.47
     entreprene
    -1.45
    �
    -1.43
    aster
    -1.42
    asters
    -1.40
    igne
    -1.40
    �
    -1.35
    �
    -1.32
     encour
    -1.31
     asteroids
    -1.28
    POSITIVE LOGITS
    IFIED
    1.29
    TING
    1.23
    https
    1.19
    SY
    1.17
    UE
    1.16
    Senior
    1.12
    LET
    1.11
    FILE
    1.10
     --
    1.10
    housing
    1.07
    Activations Density 0.405%

    No Known Activations