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. 7-ATT-KK
    6. 9423
    Prev
    Next
    INDEX
    Explanations

    references to various iPhone models and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.05
    2:0.03
    3:0.05
    4:0.04
    5:0.07
    6:0.09
    7:0.05
    8:0.08
    9:0.05
    10:0.26
    11:0.05
    Negative Logits
    natureconservancy
    -2.25
     counselors
    -2.16
     Wilderness
    -2.09
    Reviewer
    -2.03
     [&
    -2.01
    ��
    -1.90
    ��
    -1.89
     Valhalla
    -1.86
     Jonas
    -1.84
     caves
    -1.84
    POSITIVE LOGITS
    rolet
    1.99
    otype
    1.93
    andise
    1.93
     defect
    1.92
    store
    1.86
     guiActiveUn
    1.82
    iaz
    1.79
    Manufact
    1.78
    manufact
    1.77
     Factory
    1.75
    Activations Density 0.001%

    No Known Activations