© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23814
    Prev
    Next
    INDEX
    Explanations

    phrases relating to events with specific dates and locations

    oai_token-act-pair · gpt-3.5-turbo

    temporal indicators and phrases related to events or occurrences

    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
     etc
    -0.80
     EVERY
    -0.77
     Nope
    -0.70
     ðŁĻĤ
    -0.69
     ALWAYS
    -0.69
     blah
    -0.68
     goddamn
    -0.67
     darn
    -0.67
    #$
    -0.66
     creeps
    -0.66
    POSITIVE LOGITS
    resa
    1.14
    odore
    0.94
    iday
    0.90
    ogether
    0.87
    nsic
    0.85
    respond
    0.83
    wards
    0.78
    romeda
    0.76
    intendent
    0.75
    swers
    0.75
    Activations Density 0.388%

    No Known Activations