© 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. 17505
    Prev
    Next
    INDEX
    Explanations

    phrases related to recurring themes or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate recurring actions or events

    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
     @@
    -0.64
     largeDownload
    -0.63
     )]
    -0.62
    rounded
    -0.61
    mop
    -0.58
    tained
    -0.56
    orn
    -0.56
    plet
    -0.55
     Dise
    -0.55
    irtual
    -0.55
    POSITIVE LOGITS
     twice
    1.50
     frequently
    1.34
     alot
    1.32
     repeatedly
    1.31
     extensively
    1.31
     sooner
    1.27
     regularly
    1.24
     quicker
    1.21
     periodically
    1.17
     quite
    1.17
    Activations Density 1.091%

    No Known Activations