© 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. 0-RES-JB
    11. 6518
    Prev
    Next
    INDEX
    Explanations

    phrases related to data and sources

    oai_token-act-pair · gpt-3.5-turbo

    references to the day of the week, specifically "Monday"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     warrant
    -0.69
     cider
    -0.68
     retract
    -0.67
     youth
    -0.66
     piping
    -0.65
    ows
    -0.64
     space
    -0.63
     spaces
    -0.62
     checkpoint
    -0.62
     infrared
    -0.62
    POSITIVE LOGITS
    Mon
    3.75
    mon
    2.07
    MON
    1.99
    Tue
    1.90
     Mon
    1.80
    Wed
    1.69
    Fri
    1.69
     MON
    1.65
    Thu
    1.63
    monkey
    1.58
    Activations Density 0.020%

    No Known Activations