© 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. 16139
    Prev
    Next
    INDEX
    Explanations

    information related to scheduled maintenance events

    oai_token-act-pair · gpt-3.5-turbo

    scheduled maintenance announcements and updates

    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
    drug
    -0.67
    Leary
    -0.65
    stroke
    -0.64
     Humph
    -0.63
     Adolf
    -0.63
    isma
    -0.63
     instinctively
    -0.62
    SPONSORED
    -0.62
    elson
    -0.62
    Hum
    -0.62
    POSITIVE LOGITS
     update
    1.30
     updates
    1.26
     Updates
    1.10
     Update
    1.07
     release
    1.06
     updated
    1.06
     beta
    1.06
     ported
    1.04
     firmware
    1.03
     DLC
    1.01
    Activations Density 0.751%

    No Known Activations