© 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. 2-RES-JB
    11. 12463
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "sil" followed by varying numbers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to silence or quietness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hurricanes
    -0.77
     Purpose
    -0.77
     Herald
    -0.76
     Fraud
    -0.76
    OTAL
    -0.74
     Nurs
    -0.74
     Ancients
    -0.71
     Fund
    -0.70
     Care
    -0.69
     Arbor
    -0.69
    POSITIVE LOGITS
     sil
    1.15
    encing
    1.05
    encers
    1.00
    encer
    0.99
    pees
    0.93
    uted
    0.92
    iencies
    0.90
    ences
    0.88
    icon
    0.88
    enced
    0.87
    Activations Density 0.006%

    No Known Activations