© 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. 18518
    Prev
    Next
    INDEX
    Explanations

    words related to beginning or starting

    oai_token-act-pair · gpt-3.5-turbo

    references to beginnings or changes in trends or situations

    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
     wishes
    -0.73
     supervised
    -0.71
     cares
    -0.71
     loves
    -0.69
     careful
    -0.68
     lucky
    -0.68
     remembers
    -0.67
     spends
    -0.65
     SAL
    -0.64
     Doing
    -0.62
    POSITIVE LOGITS
     dawn
    1.28
     snowball
    1.20
     dissip
    1.09
     perme
    1.08
     overshadow
    1.07
     become
    1.05
     evapor
    1.04
     dwind
    1.04
     coales
    1.01
     reverber
    1.00
    Activations Density 0.190%

    No Known Activations