© 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. 22136
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named "Bud" with varying contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Bud" and related variations

    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
    pmwiki
    -0.87
    IRE
    -0.85
    SPONSORED
    -0.75
    Published
    -0.75
    Occup
    -0.72
    Definition
    -0.69
    FINEST
    -0.69
    Scotland
    -0.69
    Constructed
    -0.68
    INTER
    -0.67
    POSITIVE LOGITS
     Bud
    1.34
    gets
    1.04
    gie
    1.00
    emark
    0.87
     brewer
    0.85
    rys
    0.82
    jug
    0.80
    wig
    0.79
    rill
    0.78
    gins
    0.77
    Activations Density 0.005%

    No Known Activations