© 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. 10195
    Prev
    Next
    INDEX
    Explanations

    commonly used punctuation marks and symbols

    oai_token-act-pair · gpt-3.5-turbo

    punctuated phrases or clauses within sentences

    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
    ishly
    -0.63
    oret
    -0.61
    jah
    -0.55
    phal
    -0.54
    jured
    -0.52
    estone
    -0.52
    rik
    -0.51
    OND
    -0.51
    ingly
    -0.50
    eday
    -0.50
    POSITIVE LOGITS
     respectively
    1.00
     constitutes
    0.94
     is
    0.82
    would
    0.82
     violates
    0.81
     underscores
    0.81
    udeb
    0.80
     seems
    0.80
     amounted
    0.79
     etc
    0.79
    Activations Density 0.460%

    No Known Activations