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. 7657
    Prev
    Next
    INDEX
    Explanations

    references to content formatting and document structure

    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
    1:0.04
    2:0.03
    3:0.05
    4:0.22
    5:0.12
    6:0.06
    7:0.09
    8:0.06
    9:0.04
    10:0.04
    11:0.06
    Negative Logits
    anwhile
    -2.62
     rehears
    -2.58
     reun
    -2.39
     territ
    -2.34
     harness
    -2.31
     proble
    -2.20
     civilisation
    -2.16
     predec
    -2.16
     indo
    -2.11
    …."
    -2.10
    POSITIVE LOGITS
     [[
    3.16
     {{
    2.70
     <<
    2.65
    [[
    2.47
    Ble
    2.41
     «
    2.39
     Sz
    2.38
     Wik
    2.34
     Clone
    2.32
    Template
    2.30
    Activations Density 0.000%

    No Known Activations