© 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. 9-RES-JB
    11. 10114
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software and applications

    oai_token-act-pair · gpt-3.5-turbo

    features related to digital tools and online services for personal finance and user interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    failed
    -0.63
    arten
    -0.62
     injuring
    -0.62
     Rebell
    -0.60
     bruised
    -0.59
    eryl
    -0.58
     cited
    -0.58
    soType
    -0.57
    åħī
    -0.57
     condem
    -0.56
    POSITIVE LOGITS
     seamlessly
    1.11
     seamless
    1.08
     customizable
    1.07
     instantaneous
    1.04
     personalized
    1.00
     securely
    0.99
     offline
    0.96
     decentralized
    0.96
     interoper
    0.96
     connectivity
    0.93
    Activations Density 0.944%

    No Known Activations