© 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. 9-RES-JB
    11. 8915
    Prev
    Next
    INDEX
    Explanations

    events or occasions where something is being hosted

    oai_token-act-pair · gpt-3.5-turbo

    activities related to hosting events or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olin
    -0.77
    illard
    -0.69
    wd
    -0.65
    ondo
    -0.65
    imb
    -0.63
    lda
    -0.62
    iev
    -0.61
    aults
    -0.61
    é¾įå
    -0.61
    jab
    -0.60
    POSITIVE LOGITS
     conventions
    0.84
     guests
    0.82
     exhibitions
    0.82
    eers
    0.82
     seminars
    0.81
     weddings
    0.80
     events
    0.80
     fundra
    0.80
     gatherings
    0.79
     meetings
    0.79
    Activations Density 0.061%

    No Known Activations