© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5653
    Prev
    Next
    INDEX
    Explanations

    descriptions of beautiful or pleasant things

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to spiritual or religious concepts

    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
    •henryjames
    weird?
    •shakespeare

    No Comments

    Negative Logits
     referen
    -0.77
     corrid
    -0.76
    leneck
    -0.73
     ransomware
    -0.72
    Baby
    -0.72
     slideshow
    -0.70
     timeframe
    -0.70
     Helsinki
    -0.68
     sourcing
    -0.68
     takeaway
    -0.68
    POSITIVE LOGITS
    ,—
    1.69
     hath
    1.33
     thereof
    1.32
     unto
    1.25
     whence
    1.25
     thereto
    1.24
     ;
    1.24
     hereafter
    1.20
     thence
    1.20
    ;"
    1.18
    Activations Density 0.467%

    No Known Activations