© 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. 17091
    Prev
    Next
    INDEX
    Explanations

    references to design principles and challenges

    oai_token-act-pair · gpt-3.5-turbo

    references to design in various contexts

    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
    nikov
    -0.83
     Lauder
    -0.80
     Witnesses
    -0.78
    selves
    -0.76
    essional
    -0.75
     Arist
    -0.74
     Ago
    -0.73
    ieri
    -0.73
    ICAN
    -0.73
     Sheen
    -0.72
    POSITIVE LOGITS
    ators
    1.03
    ator
    0.96
    yout
    0.96
     design
    0.90
    ations
    0.87
    ating
    0.85
     designs
    0.85
    ates
    0.82
     flaw
    0.80
     designer
    0.78
    Activations Density 0.033%

    No Known Activations