© 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. 5585
    Prev
    Next
    INDEX
    Explanations

    words starting with "Si" followed by various combinations of letters

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Si" in various contexts

    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
    lain
    -0.95
    ãĥ¼ãĥĨ
    -0.83
    lich
    -0.76
    eers
    -0.76
    eer
    -0.74
    tenance
    -0.72
    proof
    -0.71
    ãĥ¼ãĥ«
    -0.70
    raising
    -0.69
    heimer
    -0.69
    POSITIVE LOGITS
     Si
    1.07
    Si
    0.99
    enna
    0.94
    Ti
    0.89
    pling
    0.86
    ames
    0.85
     si
    0.84
    ada
    0.82
    plin
    0.81
    RNA
    0.79
    Activations Density 0.011%

    No Known Activations