© 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. 16087
    Prev
    Next
    INDEX
    Explanations

    social media sharing options for content

    oai_token-act-pair · gpt-3.5-turbo

    phrases and symbols related to sharing content

    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
     tremend
    -0.73
     reckoning
    -0.73
     reconstruction
    -0.68
    zik
    -0.68
    quartered
    -0.68
     recon
    -0.67
     disbanded
    -0.67
     interpol
    -0.66
     repro
    -0.64
    chwitz
    -0.64
    POSITIVE LOGITS
     Pocket
    1.01
     Email
    0.96
    Pocket
    0.87
     Share
    0.84
     Tweet
    0.84
    LinkedIn
    0.83
     Twitter
    0.82
     Facebook
    0.80
     Print
    0.79
     SHARES
    0.78
    Activations Density 0.024%

    No Known Activations