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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9304
    Prev
    Next
    INDEX
    Explanations

    dates and Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    numerical dates or references that are formatted with commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expansions
    -0.91
     detectors
    -0.76
     boosters
    -0.71
     predec
    -0.71
     corridors
    -0.65
     fossils
    -0.65
     expansion
    -0.61
     conqu
    -0.61
     successors
    -0.60
     connections
    -0.59
    POSITIVE LOGITS
     2017
    1.00
     2016
    0.96
     2015
    0.95
     2014
    0.93
    000
    0.89
     2018
    0.87
     2013
    0.84
     2012
    0.82
     2010
    0.82
     2007
    0.79
    Activations Density 0.042%

    No Known Activations