© 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. 4-RES-JB
    11. 626
    Prev
    Next
    INDEX
    Explanations

    phrases related to celebrations and holidays

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to seasonal celebrations and cultural practices

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

    No Comments

    Negative Logits
    enegger
    -0.86
    ITNESS
    -0.78
    POL
    -0.72
    arella
    -0.71
    maxwell
    -0.69
    orno
    -0.68
     GOODMAN
    -0.66
    okin
    -0.66
    MODE
    -0.65
    olution
    -0.64
    POSITIVE LOGITS
    ule
    1.00
    lette
    0.99
    bum
    0.92
    cules
    0.91
    ploy
    0.82
    leted
    0.81
    clips
    0.80
    pee
    0.80
    ffe
    0.79
    kas
    0.79
    Activations Density 0.010%

    No Known Activations