© 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. 9-ATT-KK
    6. 11695
    Prev
    Next
    INDEX
    Explanations

    actions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.10
    2:0.05
    3:0.12
    4:0.10
    5:0.06
    6:0.08
    7:0.05
    8:0.05
    9:0.17
    10:0.06
    11:0.06
    Negative Logits
     Pasadena
    -2.98
    1968
    -2.79
    ward
    -2.79
    him
    -2.69
    uay
    -2.69
    his
    -2.68
    enos
    -2.67
    original
    -2.56
    rely
    -2.51
    Rex
    -2.50
    POSITIVE LOGITS
     Aden
    2.64
     blacklist
    2.58
     Acquisition
    2.52
     Clause
    2.52
     lobbying
    2.49
     Chocobo
    2.46
     neutron
    2.45
     geopolitical
    2.41
     Codex
    2.33
     SSD
    2.33
    Activations Density 0.000%

    No Known Activations