© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16230
    Prev
    Next
    INDEX
    Explanations

    date and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of dates and numerical references

    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
    ylum
    -0.67
     corrid
    -0.66
    Redd
    -0.66
     glim
    -0.65
    [[
    -0.62
    Origin
    -0.62
     paran
    -0.61
     pacif
    -0.61
    Limit
    -0.61
     ether
    -0.60
    POSITIVE LOGITS
     2013
    1.73
     2014
    1.70
     2012
    1.66
     2015
    1.61
     2011
    1.56
    2014
    1.55
    2012
    1.52
    2013
    1.51
    2011
    1.42
    2015
    1.42
    Activations Density 0.143%

    No Known Activations