© 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. 9-RES-JB
    11. 8767
    Prev
    Next
    INDEX
    Explanations

    references to news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    instances of Pokémon or fictional creatures described with various attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assum
    -0.76
     respons
    -0.69
     blah
    -0.67
     etc
    -0.67
     ie
    -0.66
     eg
    -0.63
     behav
    -0.63
    ↵Âł
    -0.63
    .*
    -0.62
     beforehand
    -0.62
    POSITIVE LOGITS
     NASCAR
    0.67
     wildfires
    0.67
    WASHINGTON
    0.67
     astronomers
    0.66
     Baltimore
    0.65
     Hillary
    0.64
     POLITICO
    0.64
    zbollah
    0.64
     Houth
    0.64
    CLUS
    0.63
    Activations Density 0.713%

    No Known Activations