© 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. 5-ATT-KK
    11. 44074
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "for" and its associated phrases

    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
    2:0.05
    3:0.06
    4:0.05
    5:0.04
    6:0.42
    7:0.03
    8:0.06
    9:0.07
    10:0.07
    11:0.05
    Negative Logits
     Channel
    -1.38
     Cly
    -1.36
    ktop
    -1.30
     orphans
    -1.18
     Picks
    -1.10
     lil
    -1.09
     Brill
    -1.08
    FTWARE
    -1.04
     knot
    -1.04
     Horde
    -1.04
    POSITIVE LOGITS
    ��
    1.79
    acus
    1.68
    oux
    1.45
    hene
    1.43
    opa
    1.42
    ón
    1.39
    cedented
    1.38
    inous
    1.38
    assault
    1.37
    utical
    1.36
    Activations Density 0.005%

    No Known Activations