© 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. 3-RES-JB
    11. 15593
    Prev
    Next
    INDEX
    Explanations

    phrases containing the sequence "Si" which could refer to names, places, or other entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions 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 @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨ
    -0.96
    lain
    -0.94
    eer
    -0.74
    lift
    -0.73
    heimer
    -0.71
    tenance
    -0.69
    enhagen
    -0.69
    raising
    -0.68
    eers
    -0.68
     Kessler
    -0.68
    POSITIVE LOGITS
     Si
    0.97
    Si
    0.92
    ames
    0.92
    inx
    0.91
    enna
    0.90
    plin
    0.87
    zech
    0.83
    pling
    0.82
    oux
    0.81
    oche
    0.80
    Activations Density 0.012%

    No Known Activations