© 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. 18519
    Prev
    Next
    INDEX
    Explanations

    instances of numerical sequences related to time frames

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of indefinite articles and expressions of quantity in a sequence

    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
     encour
    -0.72
    ATURES
    -0.69
     advances
    -0.65
    ãĤ«
    -0.65
    Instruct
    -0.63
     compliments
    -0.63
    append
    -0.62
    orem
    -0.61
     overt
    -0.61
    Contents
    -0.61
    POSITIVE LOGITS
     row
    1.34
     single
    1.11
     span
    1.02
     fortnight
    0.96
     month
    0.95
     given
    0.95
     nutshell
    0.94
     decade
    0.93
    single
    0.93
     week
    0.89
    Activations Density 0.126%

    No Known Activations