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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 18963
    Prev
    Next
    INDEX
    Explanations

    references to funding sources for research

    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
    1:0.03
    2:0.02
    3:0.07
    4:0.05
    5:0.33
    6:0.10
    7:0.08
    8:0.08
    9:0.06
    10:0.01
    11:0.02
    Negative Logits
    entimes
    -2.47
    ashing
    -2.14
     stabbing
    -2.11
    arse
    -2.08
     corros
    -2.05
    ueless
    -2.05
    oof
    -2.05
    ometimes
    -2.02
    ワン
    -1.98
     overpowered
    -1.96
    POSITIVE LOGITS
     Fellowship
    2.69
     grant
    2.65
     Donation
    2.57
     Scholarship
    2.44
     sponsor
    2.37
     Compensation
    2.32
     Sponsor
    2.32
     Spons
    2.26
     grants
    2.22
     Memorial
    2.19
    Activations Density 0.028%

    No Known Activations