© 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. 984
    Prev
    Next
    INDEX
    Explanations

    interesting and intriguing information or topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "interesting" and its variations

    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
    uxe
    -0.74
    arest
    -0.71
    reditation
    -0.69
    oise
    -0.68
    uter
    -0.67
    chen
    -0.65
    otent
    -0.64
    esp
    -0.63
    avers
    -0.63
    burgh
    -0.63
    POSITIVE LOGITS
     tid
    1.06
     juxtap
    0.99
     trivia
    0.98
    ioned
    0.88
     anecdotes
    0.87
     anecdote
    0.86
    arios
    0.84
     coincidence
    0.81
     Flavoring
    0.81
     puzzle
    0.80
    Activations Density 0.066%

    No Known Activations