© 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. 7178
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing importance or specific actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "very" and its context in various phrases

    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
     McGee
    -0.69
    Subscribe
    -0.62
    urion
    -0.61
    uchi
    -0.60
    phis
    -0.58
    blem
    -0.57
     Gund
    -0.55
    answered
    -0.54
    gre
    -0.54
    apons
    -0.54
    POSITIVE LOGITS
     least
    1.19
     outset
    1.03
     moment
    0.94
     minimum
    0.90
     pinnacle
    0.89
    stal
    0.87
     beginnings
    0.86
     forefront
    0.85
     end
    0.85
     beginning
    0.84
    Activations Density 0.014%

    No Known Activations