© 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. 14402
    Prev
    Next
    INDEX
    Explanations

    references to a specific genre or concept related to country music

    oai_token-act-pair · gpt-3.5-turbo

    references to "country."

    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
    inventoryQuantity
    -0.87
    ces
    -0.84
    Wan
    -0.77
     cumbers
    -0.74
    cial
    -0.71
    haps
    -0.71
    ovember
    -0.70
    aunder
    -0.69
    olulu
    -0.68
    thumbnails
    -0.67
    POSITIVE LOGITS
    side
    1.03
    wide
    0.91
     Country
    0.87
    Country
    0.87
    oslov
    0.83
    country
    0.81
     Publishers
    0.80
    coat
    0.79
     Manufacturer
    0.78
     Airlines
    0.78
    Activations Density 0.009%

    No Known Activations