© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14925
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and abstract terminology related to size and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.29
    2:0.06
    3:0.04
    4:0.07
    5:0.04
    6:0.05
    7:0.11
    8:0.04
    9:0.05
    10:0.06
    11:0.08
    Negative Logits
    saf
    -2.95
     Flavoring
    -2.85
     marginal
    -2.64
     tougher
    -2.53
    little
    -2.49
    cool
    -2.44
     cooler
    -2.38
     little
    -2.33
     cool
    -2.26
    )—
    -2.26
    POSITIVE LOGITS
     Large
    2.80
    yrus
    2.78
    Large
    2.71
     Metatron
    2.55
    orship
    2.52
    emale
    2.51
    large
    2.49
    imester
    2.42
     overflowing
    2.42
     DEAD
    2.42
    Activations Density 0.004%

    No Known Activations