© 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. 8-RES-JB
    11. 17760
    Prev
    Next
    INDEX
    Explanations

    references to time by focusing on words related to the "late" period

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "late," particularly in relation to historical figures or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edIn
    -0.87
     Pwr
    -0.84
    alon
    -0.76
    ebook
    -0.75
    qqa
    -0.75
    ombo
    -0.72
    erie
    -0.71
    egu
    -0.71
    henko
    -0.70
    76561
    -0.69
    POSITIVE LOGITS
     afternoon
    1.07
     twenties
    0.89
    -'
    0.85
     nights
    0.84
     adolescence
    0.83
     1960
    0.83
     evening
    0.81
     1970
    0.81
     summer
    0.80
     evenings
    0.79
    Activations Density 0.013%

    No Known Activations