© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5811
    Prev
    Next
    INDEX
    Explanations

    technology company names and product features

    oai_token-act-pair · gpt-3.5-turbo

    mentions of companies and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Marginal
    -0.78
    arial
    -0.74
    Reading
    -0.69
     confrontation
    -0.67
     NAFTA
    -0.65
     crisis
    -0.64
     crises
    -0.64
     detention
    -0.63
     unwelcome
    -0.63
     hostility
    -0.63
    POSITIVE LOGITS
     describes
    1.17
     explained
    1.16
     teased
    1.16
     explains
    1.16
     says
    1.13
     announced
    1.12
     assures
    1.10
     stated
    1.07
     intends
    1.05
     unveiled
    1.04
    Activations Density 0.277%

    No Known Activations