© 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. 11-RES-JB
    11. 20656
    Prev
    Next
    INDEX
    Explanations

    economic terms and indicators

    oai_token-act-pair · gpt-3.5-turbo

    economic growth and development indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apologise
    -0.70
     Dise
    -0.68
     Hurt
    -0.68
     Hate
    -0.68
     Fatal
    -0.65
     Problems
    -0.65
     Damage
    -0.63
     QC
    -0.63
     Causes
    -0.63
     Injury
    -0.63
    POSITIVE LOGITS
     remarkably
    1.04
     strikingly
    0.94
     boldly
    0.82
     markedly
    0.81
     nonetheless
    0.81
     undeniably
    0.80
     radically
    0.80
     enthusiastically
    0.79
     bona
    0.79
     seamlessly
    0.78
    Activations Density 0.963%

    No Known Activations