© 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. 12-RES-JB
    11. 2757
    Prev
    Next
    INDEX
    Explanations

    hashtags and Twitter handles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    everal
    -1.36
     tremend
    -1.35
     exha
    -1.34
     cumbers
    -1.31
     enthusi
    -1.29
    aditional
    -1.26
    senal
    -1.25
    ccording
    -1.24
     occas
    -1.23
    ntil
    -1.22
    POSITIVE LOGITS
     2017
    1.45
     2016
    1.30
     2018
    1.21
     2015
    1.17
     2014
    1.04
     2013
    0.98
     2019
    0.95
     2020
    0.93
    2017
    0.86
     2012
    0.85
    Activations Density 0.019%

    No Known Activations