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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 42780
    Prev
    Next
    INDEX
    Explanations

    recurring pronouns and determiners, indicating a focus on relationships and intentions within the text

    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
    2:0.05
    3:0.07
    4:0.13
    5:0.04
    6:0.11
    7:0.27
    8:0.04
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
    rouse
    -1.69
     quarry
    -1.43
     burial
    -1.41
    chers
    -1.36
    ossal
    -1.36
     pilgrims
    -1.35
    ogram
    -1.32
    utz
    -1.29
     Ferry
    -1.26
     shores
    -1.26
    POSITIVE LOGITS
     aloud
    1.68
    Spec
    1.63
    『
    1.58
    Letter
    1.51
    Reply
    1.50
     stating
    1.48
     Regarding
    1.48
     incorrectly
    1.47
    Status
    1.47
     superiority
    1.46
    Activations Density 0.008%

    No Known Activations