© 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 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. 10-RES-JB
    11. 4576
    Prev
    Next
    INDEX
    Explanations

    phrases related to importance or necessity

    oai_token-act-pair · gpt-3.5-turbo

    words indicating significance or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ograms
    -0.89
    bows
    -0.88
    ernels
    -0.87
    ULTS
    -0.86
    mails
    -0.86
    attacks
    -0.85
    lees
    -0.85
    ravings
    -0.84
    oops
    -0.84
    alks
    -0.83
    POSITIVE LOGITS
     component
    1.48
     part
    1.34
     element
    1.32
     aspect
    1.29
     contributor
    1.26
     factor
    1.26
     ingredient
    1.26
     facet
    1.22
     source
    1.19
     pillar
    1.19
    Activations Density 0.109%

    No Known Activations