© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 14534
    Prev
    Next
    INDEX
    Explanations

    words related to Sweden

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Swe" indicating a focus on a specific Swedish context or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PowerPoint
    -0.80
     LIFE
    -0.69
    ional
    -0.69
    ocl
    -0.67
     otherwise
    -0.67
     gravity
    -0.66
     Persian
    -0.66
     Minotaur
    -0.65
     reservations
    -0.65
     geography
    -0.64
    POSITIVE LOGITS
    arer
    1.14
    Swe
    1.13
     Swe
    1.12
    swe
    1.05
    izzard
    1.02
    zza
    1.01
    eping
    1.00
    cks
    0.91
    arers
    0.90
    ynes
    0.90
    Activations Density 0.008%

    No Known Activations