© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9499
    Prev
    Next
    INDEX
    Explanations

    words related to physics and physical properties

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physics and physical sciences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Imperium
    -0.94
     Siem
    -0.79
    yrinth
    -0.78
     Philips
    -0.76
     Lions
    -0.72
     Midlands
    -0.71
    umble
    -0.68
     Romania
    -0.67
     Podesta
    -0.64
    bare
    -0.64
    POSITIVE LOGITS
    icist
    1.10
    ician
    1.05
    utical
    0.98
    iology
    0.95
    OTOS
    0.91
    ically
    0.91
    Phys
    0.90
    iological
    0.90
    esville
    0.89
    kens
    0.89
    Activations Density 0.025%

    No Known Activations