© 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. 13436
    Prev
    Next
    INDEX
    Explanations

    times of day and specific events happening at those times

    oai_token-act-pair · gpt-3.5-turbo

    timestamps associated with events in descriptions

    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
    ctors
    -0.62
    alog
    -0.62
    imately
    -0.61
    iland
    -0.55
     benefited
    -0.53
    iations
    -0.53
    agues
    -0.53
    alogue
    -0.53
    sylv
    -0.52
    erella
    -0.52
    POSITIVE LOGITS
     apiece
    0.96
     behest
    0.86
    point
    0.80
    PM
    0.79
    mph
    0.78
    mast
    0.77
     intervals
    0.77
     expense
    0.75
    noon
    0.75
    pm
    0.75
    Activations Density 0.158%

    No Known Activations