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. 9572
    Prev
    Next
    INDEX
    Explanations

    references to team strength or quality

    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
    0:0.04
    1:0.05
    2:0.32
    3:0.05
    4:0.02
    5:0.03
    6:0.06
    7:0.09
    8:0.04
    9:0.05
    10:0.16
    11:0.03
    Negative Logits
     Tablet
    -2.34
    ################
    -2.33
     Letters
    -2.17
     Account
    -2.14
    ,''
    -2.13
     Telephone
    -2.10
     Charm
    -2.09
     Phone
    -2.06
    ソ
    -2.06
     Press
    -2.06
    POSITIVE LOGITS
    higher
    3.26
    Higher
    2.97
     deeper
    2.90
     higher
    2.88
    oglu
    2.82
    lower
    2.78
     newer
    2.78
     stronger
    2.68
     weaker
    2.68
     thicker
    2.63
    Activations Density 0.000%

    No Known Activations