© 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. 8-RES-JB
    11. 2579
    Prev
    Next
    INDEX
    Explanations

    mentions of attendance in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to attendance and the number of attendees at events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grave
    -0.82
    imov
    -0.79
    pex
    -0.72
    uyomi
    -0.65
    enegger
    -0.64
     penetrating
    -0.64
    deal
    -0.61
    nown
    -0.61
     prud
    -0.60
     slic
    -0.60
    POSITIVE LOGITS
     Attend
    1.14
     attendance
    1.08
     attendees
    0.99
     attend
    0.95
    enance
    0.86
     meetings
    0.83
     PAX
    0.80
    ENTS
    0.79
    ees
    0.77
     attends
    0.75
    Activations Density 0.046%

    No Known Activations