© 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. 3-RES-JB
    11. 12608
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nomine
    -0.67
     adjoining
    -0.66
     plots
    -0.64
     parap
    -0.64
     instruments
    -0.63
     scratched
    -0.63
     prolifer
    -0.62
     informants
    -0.61
     subdiv
    -0.61
     multiplication
    -0.61
    POSITIVE LOGITS
     IST
    0.99
     RELEASE
    0.95
     UTC
    0.94
    UTC
    0.88
     âĢº
    0.85
     PDT
    0.84
     EDT
    0.84
     GMT
    0.82
     partName
    0.81
     04
    0.80
    Activations Density 0.435%

    No Known Activations