© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18530
    Prev
    Next
    INDEX
    Explanations

    references to the term "Euro" followed by a single digit number, particularly the mention of "Euro 9"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Euro, particularly in a context of economic and cultural discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.75
    ////////////////
    -0.75
    20439
    -0.73
    OHN
    -0.72
    ::::::::
    -0.72
    66666666
    -0.70
    âĶĢ
    -0.70
    ::::
    -0.69
    DragonMagazine
    -0.67
    @@@@
    -0.66
    POSITIVE LOGITS
    pol
    1.00
    vision
    0.94
    pes
    0.89
     Euro
    0.88
     EUR
    0.84
    pa
    0.77
    econom
    0.75
    netic
    0.75
    trip
    0.74
    wald
    0.73
    Activations Density 0.007%

    No Known Activations