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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7666
    Prev
    Next
    INDEX
    Explanations

    event ticketing information and pricing details

    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
    0:0.32
    1:0.01
    2:0.06
    3:0.09
    4:0.04
    5:0.07
    6:0.04
    7:0.06
    8:0.04
    9:0.04
    10:0.13
    11:0.04
    Negative Logits
    Output
    -2.48
     output
    -2.43
     editing
    -2.25
     churn
    -2.23
     WRITE
    -2.22
     Task
    -2.22
     Output
    -2.20
     producing
    -2.18
     iter
    -2.06
     Jobs
    -2.06
    POSITIVE LOGITS
    querade
    2.54
     Tickets
    2.39
    ahime
    2.32
    Tickets
    2.31
    earances
    2.27
    sale
    2.24
    ickets
    2.21
    fal
    2.20
     ticket
    2.19
     SOLD
    2.19
    Activations Density 0.053%

    No Known Activations