© 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. 13653
    Prev
    Next
    INDEX
    Explanations

    conditions or situations where a specific action or substance leads to a particular outcome

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that start with "when" or "if."

    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
    lihood
    -0.70
     Dragonbound
    -0.67
    FORE
    -0.66
    PsyNetMessage
    -0.65
     Language
    -0.62
    aires
    -0.61
    aido
    -0.61
    atorium
    -0.61
    \":
    -0.61
    artisan
    -0.60
    POSITIVE LOGITS
     viewed
    1.49
     eaten
    1.46
     taken
    1.40
     handled
    1.38
     utilized
    1.36
     consumed
    1.35
     executed
    1.33
     applied
    1.31
     ingested
    1.30
     administered
    1.30
    Activations Density 0.142%

    No Known Activations