© 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. 8-RES-JB
    11. 6267
    Prev
    Next
    INDEX
    Explanations

    technical terms related to coding and programming

    oai_token-act-pair · gpt-3.5-turbo

    discussions of positive outcomes and benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inappropriate
    -0.62
    bent
    -0.61
    entary
    -0.60
    ifice
    -0.59
     delinquent
    -0.59
     stalk
    -0.57
     Inquiry
    -0.57
     inconsist
    -0.57
    uca
    -0.56
     inco
    -0.56
    POSITIVE LOGITS
     improved
    1.02
     improves
    0.97
    Improve
    0.92
     improvements
    0.90
     revital
    0.89
    Improved
    0.87
     rejuven
    0.87
     Improved
    0.84
     congratulate
    0.84
     improvement
    0.83
    Activations Density 1.713%

    No Known Activations