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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 18616
    Prev
    Next
    INDEX
    Explanations

    words related to consumer products and health-related advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.03
    2:0.06
    3:0.34
    4:0.07
    5:0.08
    6:0.02
    7:0.06
    8:0.04
    9:0.02
    10:0.11
    11:0.06
    Negative Logits
     presently
    -2.24
     pending
    -2.24
    umerable
    -2.19
    ranking
    -2.16
     correspondent
    -2.13
     publication
    -2.10
     broadcaster
    -2.09
    umerous
    -2.09
     transcript
    -2.07
     commentator
    -2.06
    POSITIVE LOGITS
     Eating
    2.53
     Wonderland
    2.51
     Yourself
    2.46
     Pigs
    2.45
     Your
    2.42
     Spice
    2.33
     Relax
    2.28
     Bubble
    2.28
     Cookies
    2.27
     Taste
    2.23
    Activations Density 0.080%

    No Known Activations