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. 18796
    Prev
    Next
    INDEX
    Explanations

    numerical values and identifiers in a document

    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
    1:0.07
    2:0.33
    3:0.04
    4:0.03
    5:0.02
    6:0.06
    7:0.07
    8:0.05
    9:0.02
    10:0.19
    11:0.04
    Negative Logits
    perature
    -2.67
    ippi
    -2.60
    CS
    -2.53
     Cohn
    -2.52
    rica
    -2.46
    rition
    -2.46
    thia
    -2.43
    NetMessage
    -2.42
     Crosby
    -2.35
    rist
    -2.35
    POSITIVE LOGITS
     unman
    3.41
     Un
    3.40
    un
    3.39
     unaff
    3.23
    Un
    3.23
     unden
    3.16
     un
    3.13
     unequ
    3.11
     UN
    3.08
    UN
    3.07
    Activations Density 0.001%

    No Known Activations