© 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. 0-RES-JB
    11. 16713
    Prev
    Next
    INDEX
    Explanations

    rare items or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rarity and scarcity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     volunt
    -0.76
     wire
    -0.72
     mat
    -0.71
     maid
    -0.68
     sod
    -0.68
     bodily
    -0.67
    iew
    -0.66
     substitution
    -0.65
     oper
    -0.63
     streams
    -0.63
    POSITIVE LOGITS
     Rare
    3.46
    Rare
    3.29
    Uncommon
    2.39
     Uncommon
    2.20
    Legendary
    1.70
     Legendary
    1.62
    Common
    1.58
     Relic
    1.46
     rarity
    1.41
     rare
    1.39
    Activations Density 0.038%

    No Known Activations