© 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. 10-RES-JB
    11. 3158
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or activities happening within a community

    oai_token-act-pair · gpt-3.5-turbo

    events that are significant or well-established, often related to festivals or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elligence
    -0.85
    llular
    -0.79
    illus
    -0.78
    utenant
    -0.75
     Folder
    -0.75
    Letter
    -0.75
    oan
    -0.74
    Lie
    -0.73
    Analysis
    -0.72
    opathy
    -0.71
    POSITIVE LOGITS
     festival
    1.89
     attendees
    1.87
     organizers
    1.81
     organisers
    1.80
     attendance
    1.73
     venue
    1.71
     venues
    1.59
     festivals
    1.58
     festivities
    1.56
     Festival
    1.52
    Activations Density 0.831%

    No Known Activations