© 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. 11-RES-JB
    11. 7745
    Prev
    Next
    INDEX
    Explanations

    comments and reviews, potentially related to online forums or feedback websites

    oai_token-act-pair · gpt-3.5-turbo

    formatting related to user-generated content and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.82
    issued
    -0.69
    worthiness
    -0.66
    anticipated
    -0.64
     separately
    -0.64
    entimes
    -0.64
    setting
    -0.64
     controls
    -0.63
    MORE
    -0.63
     textbooks
    -0.63
    POSITIVE LOGITS
     Anonymous
    1.23
     john
    1.20
     david
    1.19
    Anonymous
    1.07
     dan
    1.06
     dj
    1.06
     kb
    1.05
     jo
    1.03
    jon
    1.02
    mr
    1.02
    Activations Density 0.197%

    No Known Activations