© 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. 13588
    Prev
    Next
    INDEX
    Explanations

    adjectives describing positive qualities or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    expressions of moderate to high enthusiasm or positivity about subjects, particularly using the word "pretty."

    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
    upon
    -0.82
    venant
    -0.80
    APD
    -0.79
     FTA
    -0.73
    arta
    -0.72
    KY
    -0.71
    pent
    -0.69
    HAEL
    -0.68
    jen
    -0.68
    alez
    -0.67
    POSITIVE LOGITS
     darn
    1.26
     nifty
    0.97
     much
    0.89
     damn
    0.87
     tasty
    0.85
     harmless
    0.85
    nice
    0.84
     straightforward
    0.83
     neat
    0.81
     awesome
    0.80
    Activations Density 0.019%

    No Known Activations