© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21487
    Prev
    Next
    INDEX
    Explanations

    terms related to identification and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.25
    3:0.07
    4:0.15
    5:0.04
    6:0.03
    7:0.03
    8:0.07
    9:0.11
    10:0.07
    11:0.04
    Negative Logits
    imar
    -1.69
    ldon
    -1.54
    velt
    -1.52
    interstitial
    -1.36
    asionally
    -1.31
    umph
    -1.30
    laughs
    -1.30
    usc
    -1.28
    terson
    -1.27
     Mehran
    -1.23
    POSITIVE LOGITS
     Orient
    1.31
     Transgender
    1.28
     Tactical
    1.23
     Psycho
    1.20
     Predict
    1.19
     MacArthur
    1.19
    ibles
    1.19
     Incident
    1.16
     PTSD
    1.16
    agnetic
    1.15
    Activations Density 0.005%

    No Known Activations