© 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. 9-RES-JB
    11. 17628
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical processes and their effects on the environment

    oai_token-act-pair · gpt-3.5-turbo

    scientific explanations related to physical processes and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wag
    -0.79
     Cosponsors
    -0.74
    TW
    -0.73
     Lessons
    -0.73
     Franch
    -0.72
    ruary
    -0.69
    onomy
    -0.69
    Privacy
    -0.69
    Community
    -0.67
     Lans
    -0.66
    POSITIVE LOGITS
     nutrients
    1.11
    llular
    1.08
     oxid
    1.07
     nutrient
    1.06
     calcium
    1.05
     acidic
    1.04
     metabolic
    1.03
     molecules
    1.03
     oxidation
    1.02
     oxidative
    1.02
    Activations Density 0.478%

    No Known Activations