© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 6983
    Prev
    Next
    INDEX
    Explanations

    names of years in historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    dates associated with significant historical events

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

    No Comments

    Negative Logits
     pse
    -0.68
    onite
    -0.64
    aturday
    -0.63
     mutually
    -0.63
     porous
    -0.63
     STL
    -0.59
     booth
    -0.59
     contiguous
    -0.58
     substrate
    -0.57
    cko
    -0.57
    POSITIVE LOGITS
     onwards
    0.80
     onward
    0.75
    chev
    0.73
    -'
    0.73
    士
    0.71
    çļ
    0.70
    âĶĢâĶĢâĶĢâĶĢ
    0.67
    .............
    0.65
     Mechdragon
    0.64
    GMT
    0.64
    Activations Density 0.060%

    No Known Activations