© 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. 23445
    Prev
    Next
    INDEX
    Explanations

    references to Bitcoin and cryptocurrency-related discussions

    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
    1:0.14
    2:0.07
    3:0.06
    4:0.09
    5:0.09
    6:0.05
    7:0.08
    8:0.06
    9:0.13
    10:0.07
    11:0.03
    Negative Logits
    wagon
    -2.04
    aukee
    -1.97
    hower
    -1.95
    ggie
    -1.78
    pez
    -1.76
    ichick
    -1.75
     Hitchcock
    -1.70
     Confederate
    -1.68
    mire
    -1.67
    hovah
    -1.67
    POSITIVE LOGITS
    Desk
    2.11
     Razer
    1.92
    Platform
    1.74
     Sina
    1.72
     Bit
    1.71
    Software
    1.71
    "},"
    1.69
     Raz
    1.66
     platforms
    1.65
     Reuters
    1.61
    Activations Density 0.001%

    No Known Activations