© 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. 6-RES-JB
    11. 13793
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce or explain visual content

    oai_token-act-pair · gpt-3.5-turbo

    phrases suggesting the reader's perspective or engagement in an explanation

    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
    emate
    -0.64
     Ducks
    -0.62
     Deng
    -0.61
    lasting
    -0.61
    rang
    -0.60
     Pistons
    -0.60
    enberg
    -0.59
    wr
    -0.59
    wcs
    -0.59
     Penguins
    -0.59
    POSITIVE LOGITS
     guessed
    0.76
    Know
    0.72
     yourselves
    0.70
     realise
    0.67
    Figure
    0.64
     paraph
    0.64
     wont
    0.64
    :{
    0.63
     Know
    0.63
     insure
    0.60
    Activations Density 0.060%

    No Known Activations