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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 45129
    Prev
    Next
    INDEX
    Explanations

    critical scientific concepts and formal definitions

    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
    0:0.02
    1:0.03
    2:0.22
    3:0.16
    4:0.12
    5:0.02
    6:0.12
    7:0.04
    8:0.04
    9:0.04
    10:0.10
    11:0.04
    Negative Logits
    gdala
    -1.95
    athing
    -1.55
    bara
    -1.52
    rogram
    -1.46
    amily
    -1.46
    ongevity
    -1.43
    onut
    -1.43
    ovan
    -1.42
    psons
    -1.31
    thren
    -1.30
    POSITIVE LOGITS
     euphem
    1.73
     incidentally
    1.47
    *)
    1.46
    ?)
    1.46
    ?).
    1.45
     conducive
    1.41
     precursor
    1.41
     ideally
    1.39
    )."
    1.39
     condu
    1.36
    Activations Density 0.120%

    No Known Activations