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. 3200
    Prev
    Next
    INDEX
    Explanations

    integral parts of a narrative or occurrences that initiate a story or complex sequence

    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
    0:0.12
    1:0.01
    2:0.03
    3:0.03
    4:0.05
    5:0.03
    6:0.23
    7:0.03
    8:0.06
    9:0.31
    10:0.01
    11:0.02
    Negative Logits
     RI
    -3.65
    uri
    -3.59
    URI
    -3.56
     Shiva
    -3.52
     PsyNet
    -3.46
     vibr
    -3.42
     irrig
    -3.31
     Pratt
    -3.21
     Yak
    -3.15
     ion
    -3.15
    POSITIVE LOGITS
    Mac
    10.20
     Mac
    9.79
    mac
    8.46
    MAC
    8.27
     MAC
    8.20
     mac
    7.95
     Macintosh
    7.64
     MacDonald
    7.59
     macros
    6.05
     macOS
    5.79
    Activations Density 0.021%

    No Known Activations