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. 44239
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal experiences or statements about knowledge and perception

    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
    0:0.02
    1:0.01
    2:0.22
    3:0.09
    4:0.15
    5:0.03
    6:0.06
    7:0.06
    8:0.04
    9:0.05
    10:0.11
    11:0.10
    Negative Logits
    uberty
    -1.86
    aughtered
    -1.79
    BAT
    -1.65
    TIT
    -1.63
    EngineDebug
    -1.49
    ategory
    -1.48
     Lethal
    -1.47
    tle
    -1.46
    lethal
    -1.44
    ename
    -1.43
    POSITIVE LOGITS
     EVER
    2.10
     ever
    2.00
     imaginable
    1.68
     ded
    1.58
     faire
    1.56
    fters
    1.54
     deduct
    1.51
     sorely
    1.47
     compliment
    1.44
     fram
    1.42
    Activations Density 0.011%

    No Known Activations