© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 360
    Prev
    Next
    INDEX
    Explanations

    phrases related to replacement or substitution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.05
    2:0.26
    3:0.05
    4:0.03
    5:0.04
    6:0.12
    7:0.03
    8:0.03
    9:0.19
    10:0.03
    11:0.02
    Negative Logits
     Kafka
    -3.27
     chill
    -3.24
    amy
    -3.17
     clouds
    -3.14
     Guinness
    -3.11
     zoning
    -3.05
     Blaz
    -2.96
     Booth
    -2.95
     voy
    -2.91
     secrecy
    -2.89
    POSITIVE LOGITS
     replacements
    8.26
     Replacement
    7.96
     replacement
    7.85
    Repl
    7.54
    repl
    7.10
     Replace
    7.04
     replace
    6.84
     replaced
    6.70
     Repl
    6.54
    replace
    6.41
    Activations Density 0.023%

    No Known Activations