© 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. 2-RES-JB
    11. 5561
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "regular season" in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    references to a "regular season" in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sov
    -0.79
    UST
    -0.78
    IDA
    -0.78
    NRS
    -0.78
    FG
    -0.74
    ï¸ı
    -0.73
    IRO
    -0.71
    ³³³³³³³³³³³³³³³³
    -0.71
    lda
    -0.70
     Specific
    -0.70
    POSITIVE LOGITS
    ity
    0.97
    ised
    0.95
    isation
    0.88
    isations
    0.86
     occurrence
    0.86
     weekday
    0.82
    oshenko
    0.82
    isers
    0.82
     appearances
    0.82
     weekly
    0.81
    Activations Density 0.007%

    No Known Activations