© 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. 5056
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to molecules and molecular structures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to molecules and their structures

    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
    swick
    -0.82
    į
    -0.80
    Disney
    -0.78
    ļé
    -0.76
    visors
    -0.76
    ²
    -0.73
    san
    -0.70
    grim
    -0.70
     Freddy
    -0.67
    rek
    -0.67
    POSITIVE LOGITS
    cules
    1.28
     molecules
    1.20
     molecule
    1.20
     nitrogen
    1.05
    cule
    0.93
     oxygen
    0.89
    agine
    0.88
     chemically
    0.87
     atoms
    0.86
     chemistry
    0.86
    Activations Density 0.029%

    No Known Activations