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. 18975
    Prev
    Next
    INDEX
    Explanations

    terms related to music albums and their reviews

    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
    0:0.08
    1:0.08
    2:0.08
    3:0.09
    4:0.08
    5:0.08
    6:0.07
    7:0.08
    8:0.07
    9:0.07
    10:0.09
    11:0.07
    Negative Logits
     Writers
    -2.29
     commerce
    -2.20
     circulation
    -2.20
     Journalists
    -2.16
     Papers
    -2.16
     circ
    -2.15
     borne
    -2.14
     Industry
    -2.11
     Graphic
    -2.09
     medi
    -2.08
    POSITIVE LOGITS
    tek
    2.50
    bah
    2.28
    vik
    2.24
    urated
    2.22
    fried
    2.22
    adiq
    2.21
    マ
    2.17
    bash
    2.15
    lees
    2.15
    keley
    2.15
    Activations Density 0.000%

    No Known Activations