© 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. 2-RES-JB
    11. 8957
    Prev
    Next
    INDEX
    Explanations

    specific issues or topics mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to pressing societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urses
    -0.82
    achev
    -0.79
    bsite
    -0.79
    ellow
    -0.77
    alt
    -0.75
    bered
    -0.74
    jin
    -0.74
    berman
    -0.73
    glas
    -0.73
    htaking
    -0.72
    POSITIVE LOGITS
     issue
    0.84
    Issue
    0.83
    naires
    0.81
    DonaldTrump
    0.74
     plag
    0.72
     Issues
    0.70
     Issue
    0.70
     HRC
    0.70
    Problem
    0.69
     tracker
    0.68
    Activations Density 0.039%

    No Known Activations