© 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. 22836
    Prev
    Next
    INDEX
    Explanations

    names related to different individuals named Simon

    oai_token-act-pair · gpt-3.5-turbo

    the name "Simon" and its related variations

    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
    ngth
    -0.74
    giving
    -0.69
    REE
    -0.65
    VR
    -0.64
     Alz
    -0.62
    LEY
    -0.62
    hole
    -0.61
    ÃĽ
    -0.60
     Pist
    -0.60
    esome
    -0.60
    POSITIVE LOGITS
    imon
    1.05
    omon
    1.03
    ihilation
    1.00
    ial
    0.95
    amon
    0.92
    ica
    0.89
    etary
    0.88
    ails
    0.87
    iod
    0.86
    eless
    0.86
    Activations Density 0.013%

    No Known Activations