© 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. 13567
    Prev
    Next
    INDEX
    Explanations

    officials or professionals mentioned in a news-like context

    oai_token-act-pair · gpt-3.5-turbo

    references to authority figures or organizations involved in official capacities

    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
    ãĥĸ
    -0.68
    cast
    -0.66
    good
    -0.64
    liest
    -0.62
    ces
    -0.62
    co
    -0.62
    TON
    -0.62
    DonaldTrump
    -0.61
     Oval
    -0.61
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.60
    POSITIVE LOGITS
     confir
    0.85
     encount
    0.84
     raided
    0.79
     learned
    0.79
     sugg
    0.79
    poons
    0.78
     consulted
    0.77
     investigating
    0.77
     speculate
    0.74
     oun
    0.74
    Activations Density 0.143%

    No Known Activations