© 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. 18314
    Prev
    Next
    INDEX
    Explanations

    words related to rarity or infrequency

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rare" and its context in various phrases

    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
    fulness
    -0.66
    iston
    -0.65
    fuck
    -0.65
     Extend
    -0.63
    Vote
    -0.63
    ysc
    -0.63
    keeping
    -0.63
    strap
    -0.62
    src
    -0.62
    WAY
    -0.61
    POSITIVE LOGITS
     rare
    3.72
     uncommon
    2.03
    Rare
    2.03
     rarity
    2.00
     Rare
    1.99
     scarce
    1.41
     unusual
    1.41
    Uncommon
    1.39
     rarely
    1.33
     unheard
    1.29
    Activations Density 0.019%

    No Known Activations