© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11212
    Prev
    Next
    INDEX
    Explanations

    dollar amounts or financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods at the end of 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
     selfie
    -0.86
     microbiome
    -0.86
    plet
    -0.81
     compet
    -0.79
     emoji
    -0.79
    yip
    -0.78
     genders
    -0.77
     dips
    -0.77
     vape
    -0.75
     upgr
    -0.74
    POSITIVE LOGITS
     Eventually
    1.77
     Shortly
    1.65
     Soon
    1.57
     Later
    1.56
     Afterwards
    1.54
     Initially
    1.47
     Ultimately
    1.47
     Accordingly
    1.47
     Consequently
    1.46
     Fortunately
    1.43
    Activations Density 0.346%

    No Known Activations