© 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. 3068
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a punctuation mark, especially periods

    oai_token-act-pair · gpt-3.5-turbo

    sentences that highlight issues or topics of concern

    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
     extinct
    -0.88
     ageing
    -0.81
     purse
    -0.81
     regener
    -0.77
     regenerate
    -0.77
     graveyard
    -0.76
     glim
    -0.76
     cellar
    -0.76
     ecosystem
    -0.75
     overhead
    -0.75
    POSITIVE LOGITS
     Emails
    1.14
     Specifically
    1.10
     Apparently
    1.10
     Asked
    1.08
     Though
    1.07
     Later
    1.07
     Instead
    1.06
     Notably
    1.06
     Meanwhile
    1.03
     However
    1.03
    Activations Density 0.748%

    No Known Activations