© 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. 3318
    Prev
    Next
    INDEX
    Explanations

    commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dates in the format of month, day, and year

    oai_token-act-pair · gpt-3.5-turbo
    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
     corridors
    -0.64
     conferences
    -0.61
     detectors
    -0.59
     seam
    -0.57
     Centauri
    -0.57
     terminals
    -0.55
     headaches
    -0.54
     boosters
    -0.54
    paio
    -0.54
     marines
    -0.53
    POSITIVE LOGITS
     2017
    1.28
     2015
    1.20
     2016
    1.17
     2014
    1.16
     2018
    1.14
     2013
    1.09
     2012
    1.03
    2017
    0.98
     2010
    0.98
     2011
    0.97
    Activations Density 0.030%

    No Known Activations