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. 5-ATT-KK
    6. 44385
    Prev
    Next
    INDEX
    Explanations

    references to data and statistics in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.09
    3:0.08
    4:0.15
    5:0.03
    6:0.05
    7:0.22
    8:0.05
    9:0.03
    10:0.08
    11:0.14
    Negative Logits
    oral
    -1.69
    ORE
    -1.55
    pressed
    -1.48
    orers
    -1.48
    educ
    -1.39
    EngineDebug
    -1.38
    operated
    -1.37
    aired
    -1.36
    PRO
    -1.35
    strip
    -1.32
    POSITIVE LOGITS
    hner
    1.51
     originals
    1.47
     Tsukuyomi
    1.45
     altogether
    1.39
     fatalities
    1.39
     extant
    1.38
     sources
    1.38
     previous
    1.31
     casualties
    1.30
     suicides
    1.30
    Activations Density 0.003%

    No Known Activations