© 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. 13675
    Prev
    Next
    INDEX
    Explanations

    phrases indicating important or noteworthy information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities or occurrences

    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
    emale
    -0.74
    vid
    -0.73
    raid
    -0.72
    eton
    -0.71
    ride
    -0.71
    ossier
    -0.71
    vest
    -0.69
    é¾įåĸļ士
    -0.68
    imaru
    -0.67
    querade
    -0.66
    POSITIVE LOGITS
     interesting
    1.18
     serious
    1.12
     nifty
    1.12
     surprises
    1.09
     surprising
    1.06
     semblance
    1.06
     pretty
    1.04
     intriguing
    1.03
     awfully
    1.03
     incredible
    1.03
    Activations Density 0.090%

    No Known Activations