© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 3795
    Prev
    Next
    INDEX
    Explanations

    words related to household appliances

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of appliances and their features

    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
    lot
    -0.77
    bos
    -0.77
    ffiti
    -0.77
    pac
    -0.75
    tering
    -0.72
    nda
    -0.71
    lock
    -0.70
     Pad
    -0.70
    maps
    -0.69
    Po
    -0.69
    POSITIVE LOGITS
     appliance
    0.91
     Appl
    0.82
    itness
    0.74
     appliances
    0.73
     simultane
    0.70
    ^^^^
    0.68
    uous
    0.67
    rador
    0.67
    ^^
    0.67
     transformer
    0.66
    Activations Density 0.035%

    No Known Activations