© 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. 10-RES-JB
    11. 12242
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and software development

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to web security, automation, and configuration management

    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
    EStream
    -0.86
    soType
    -0.86
    answer
    -0.84
    oiler
    -0.79
    ItemThumbnailImage
    -0.77
    isSpecialOrderable
    -0.75
    ":""},{"
    -0.74
    otomy
    -0.74
    rition
    -0.72
    çīĪ
    -0.72
    POSITIVE LOGITS
     applications
    0.93
     objects
    0.91
     your
    0.91
     unwanted
    0.87
     multimedia
    0.86
     portfolios
    0.86
     datasets
    0.86
     productivity
    0.83
     complex
    0.83
     WordPress
    0.83
    Activations Density 0.356%

    No Known Activations