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. 20657
    Prev
    Next
    INDEX
    Explanations

    instances of the word "friend."

    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
    0:0.08
    1:0.07
    2:0.08
    3:0.07
    4:0.08
    5:0.08
    6:0.07
    7:0.08
    8:0.07
    9:0.08
    10:0.08
    11:0.09
    Negative Logits
    anuts
    -3.34
     Flavoring
    -2.66
    uten
    -2.59
    ando
    -2.57
     trailers
    -2.56
     HUD
    -2.56
     Mazda
    -2.52
     cannabin
    -2.50
    imity
    -2.50
     Disapp
    -2.46
    POSITIVE LOGITS
    gal
    2.95
     GOODMAN
    2.88
     facult
    2.66
    =#
    2.61
    helps
    2.55
     symp
    2.48
     whistlebl
    2.38
    JD
    2.35
    obb
    2.27
    writ
    2.26
    Activations Density 0.000%

    No Known Activations