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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43366
    Prev
    Next
    INDEX
    Explanations

    references to animal cubs, particularly in terms of their age and quantity

    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
    1:0.04
    2:0.06
    3:0.05
    4:0.05
    5:0.06
    6:0.05
    7:0.05
    8:0.04
    9:0.09
    10:0.32
    11:0.10
    Negative Logits
     alk
    -1.90
     ammon
    -1.74
     wastewater
    -1.70
     vapor
    -1.68
     fluor
    -1.67
     manufactures
    -1.61
     roadside
    -1.53
     manufacture
    -1.52
     transformer
    -1.48
     pollutants
    -1.47
    POSITIVE LOGITS
    rentices
    2.01
    thood
    1.90
    requisites
    1.82
    requisite
    1.73
    itled
    1.67
    zees
    1.63
    oké
    1.59
    skill
    1.58
    irement
    1.57
    chieve
    1.56
    Activations Density 0.000%

    No Known Activations