© 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. 1777
    Prev
    Next
    INDEX
    Explanations

    medical and research-related terms, particularly focusing on study designs and methods

    oai_token-act-pair · gpt-3.5-turbo

    references to psychological studies and methodologies

    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
    shit
    -0.77
    kids
    -0.76
    Connector
    -0.74
     messing
    -0.73
    Rain
    -0.70
     greens
    -0.70
    rub
    -0.69
    enery
    -0.68
    atron
    -0.68
    belt
    -0.68
    POSITIVE LOGITS
     heterogeneity
    1.10
     hypothesized
    1.05
     assay
    1.05
     âĪ¼
    1.01
     methodological
    1.01
     clinical
    1.00
     PLoS
    1.00
     clinically
    0.99
     analyses
    0.98
     phenotype
    0.96
    Activations Density 0.876%

    No Known Activations