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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7102
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters often found in text formatting or coding

    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
    0:0.05
    1:0.01
    2:0.08
    3:0.06
    4:0.05
    5:0.03
    6:0.22
    7:0.11
    8:0.04
    9:0.05
    10:0.14
    11:0.10
    Negative Logits
     specificity
    -1.61
     mustache
    -1.55
    utenberg
    -1.46
     coma
    -1.36
     situational
    -1.32
     consistency
    -1.30
     toughness
    -1.29
     coffin
    -1.29
     bitterness
    -1.29
     complexity
    -1.27
    POSITIVE LOGITS
    export
    1.64
    �
    1.63
    Pacific
    1.57
    �
    1.49
    �
    1.47
    �
    1.47
    ombat
    1.43
    GMT
    1.43
    グ
    1.43
    り
    1.41
    Activations Density 0.003%

    No Known Activations