© 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. 4-RES-JB
    11. 696
    Prev
    Next
    INDEX
    Explanations

    hyperlinks to tweets

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, specifically periods

    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
     induct
    -0.75
     involuntary
    -0.74
     audits
    -0.73
     assessments
    -0.72
     tenants
    -0.71
     acceptance
    -0.70
     awakening
    -0.69
     studies
    -0.68
     warranties
    -0.68
     acquisitions
    -0.68
    POSITIVE LOGITS
    twitter
    1.50
    cdn
    1.08
    facebook
    1.03
     Retrieved
    0.96
    nz
    0.93
    imgur
    0.92
    gov
    0.90
    github
    0.89
    cpp
    0.88
    google
    0.87
    Activations Density 0.054%

    No Known Activations