© 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. 10-RES-JB
    11. 15992
    Prev
    Next
    INDEX
    Explanations

    words related to gaining popularity, acceptance, or support

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of gaining popularity or acceptance over time

    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
    merce
    -0.72
     Alone
    -0.71
    aughty
    -0.70
    mini
    -0.68
    owship
    -0.65
     Audit
    -0.65
    Community
    -0.65
    CAP
    -0.62
     Emails
    -0.62
    azo
    -0.61
    POSITIVE LOGITS
     prominence
    1.20
     significance
    1.18
     relevance
    1.13
     traction
    1.11
     adherents
    1.09
     momentum
    1.04
     fruition
    1.04
     urgency
    1.03
     impetus
    1.03
     importance
    1.01
    Activations Density 0.232%

    No Known Activations