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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20646
    Prev
    Next
    INDEX
    Explanations

    names and titles associated with movies, shows, and characters

    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
    0:0.07
    1:0.01
    2:0.03
    3:0.23
    4:0.02
    5:0.05
    6:0.03
    7:0.04
    8:0.03
    9:0.02
    10:0.39
    11:0.04
    Negative Logits
     opportunity
    -2.39
     opportunities
    -2.25
     imposes
    -2.13
     chance
    -2.11
     restrictions
    -2.08
     aims
    -2.06
     wishes
    -2.03
     requests
    -1.99
     needs
    -1.99
     necessities
    -1.98
    POSITIVE LOGITS
    !),
    2.49
    ,)
    2.49
    )!
    2.46
    ),
    2.38
    ?),
    2.33
    hift
    2.32
    /)
    2.31
    -)
    2.19
    !)
    2.18
    ),"
    2.09
    Activations Density 0.047%

    No Known Activations