© 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. 15864
    Prev
    Next
    INDEX
    Explanations

    references to beta testing

    oai_token-act-pair · gpt-3.5-turbo

    references to beta testing and related phases in software development

    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
     ................
    -0.77
    manship
    -0.73
    ill
    -0.70
     Wrest
    -0.69
    Jew
    -0.68
     Petr
    -0.67
    iture
    -0.67
    uman
    -0.66
     Saud
    -0.64
    nesses
    -0.64
    POSITIVE LOGITS
     beta
    3.79
     Beta
    2.95
    Beta
    2.72
    beta
    2.71
     alpha
    2.28
    alpha
    1.84
     Alpha
    1.63
     gamma
    1.63
     β
    1.63
    Alpha
    1.60
    Activations Density 0.023%

    No Known Activations