© 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. 11-RES-JB
    11. 7799
    Prev
    Next
    INDEX
    Explanations

    dates in the format mm/dd/yyyy

    oai_token-act-pair · gpt-3.5-turbo

    dates and numbers in the form of updates or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     steroids
    -0.77
     brim
    -0.68
     Fidel
    -0.68
     sooner
    -0.66
     duty
    -0.66
     bribes
    -0.66
     sheep
    -0.64
     Cyan
    -0.64
     sucker
    -0.64
     indo
    -0.64
    POSITIVE LOGITS
    2018
    2.08
    2017
    1.99
    2014
    1.93
    2016
    1.92
    2015
    1.92
    2013
    1.90
    2012
    1.89
    2011
    1.86
    2010
    1.82
    2009
    1.80
    Activations Density 0.026%

    No Known Activations