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. 5-ATT-KK
    6. 44089
    Prev
    Next
    INDEX
    Explanations

    references to numerical or statistical data

    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
    0:0.03
    1:0.02
    2:0.09
    3:0.04
    4:0.10
    5:0.02
    6:0.27
    7:0.20
    8:0.02
    9:0.03
    10:0.09
    11:0.04
    Negative Logits
    ouver
    -1.76
    ifest
    -1.61
    omaly
    -1.57
     uphill
    -1.56
    venants
    -1.51
    aris
    -1.50
    auld
    -1.48
    onew
    -1.48
     snowball
    -1.47
    ourses
    -1.44
    POSITIVE LOGITS
    ْ
    1.55
     Ratings
    1.52
     expired
    1.48
     Quantity
    1.45
    specified
    1.39
    abba
    1.39
    tainment
    1.38
     Tens
    1.30
    ptives
    1.27
     Minion
    1.27
    Activations Density 0.000%

    No Known Activations