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. 27877
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the existence or state of being

    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
    0:0.02
    1:0.01
    2:0.16
    3:0.08
    4:0.07
    5:0.05
    6:0.14
    7:0.04
    8:0.03
    9:0.03
    10:0.10
    11:0.20
    Negative Logits
     Tycoon
    -1.60
     Animation
    -1.52
     rewriting
    -1.39
     Lynd
    -1.36
     coron
    -1.36
     frontrunner
    -1.33
     NX
    -1.31
     rewrite
    -1.30
    Reviewer
    -1.28
     Generations
    -1.27
    POSITIVE LOGITS
    irin
    1.79
    apor
    1.54
    enza
    1.54
     pleas
    1.48
    DERR
    1.47
    Temp
    1.45
    abl
    1.44
    uti
    1.40
    reet
    1.40
    alsa
    1.38
    Activations Density 0.003%

    No Known Activations