© 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. 566
    Prev
    Next
    INDEX
    Explanations

    phrases related to film critiques and comparisons

    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
    0:0.13
    1:0.02
    2:0.16
    3:0.20
    4:0.03
    5:0.11
    6:0.02
    7:0.10
    8:0.05
    9:0.02
    10:0.09
    11:0.02
    Negative Logits
     receipt
    -2.47
    Fax
    -2.38
     contacts
    -2.29
    contact
    -2.26
    fax
    -2.24
    Protect
    -2.22
    address
    -2.11
    LinkedIn
    -2.11
     contact
    -2.10
    achusetts
    -2.10
    POSITIVE LOGITS
     genre
    3.83
     cinematic
    3.70
     nostalgia
    3.63
    genre
    3.38
     nostalgic
    3.32
     sequels
    3.31
     genres
    3.22
     creatively
    3.18
     enjoyable
    3.10
     immersive
    3.02
    Activations Density 0.701%

    No Known Activations