© 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. 2267
    Prev
    Next
    INDEX
    Explanations

    comma punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    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
    imize
    -0.83
    urized
    -0.76
    imeter
    -0.75
    ãĤ©
    -0.73
    colored
    -0.72
    rollment
    -0.71
    adena
    -0.70
    DAQ
    -0.70
    bors
    -0.69
    imeters
    -0.69
    POSITIVE LOGITS
     whilst
    1.51
     Whilst
    1.21
     emphas
    1.17
     ITV
    1.16
     criticised
    1.09
     organisers
    1.09
     BBC
    1.08
     apologise
    1.08
     campaigners
    1.06
     fuelled
    1.06
    Activations Density 0.269%

    No Known Activations