© 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. 10-RES-JB
    11. 10253
    Prev
    Next
    INDEX
    Explanations

    phrases involving legal or political entities and actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, specifically periods and associated abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     levers
    -0.70
     opera
    -0.69
     friendly
    -0.65
     universally
    -0.62
     fibre
    -0.60
     provoking
    -0.59
     competence
    -0.58
     theat
    -0.58
     emot
    -0.58
     fer
    -0.58
    POSITIVE LOGITS
    Va
    1.04
    Gray
    0.96
    rex
    0.90
     Luffy
    0.80
    RAW
    0.76
     Rockefeller
    0.76
    C
    0.73
    anton
    0.70
    iamond
    0.69
     Roosevelt
    0.69
    Activations Density 0.025%

    No Known Activations