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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10077
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to computer hardware and processors

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and comparisons related to computer processors

    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
    iquette
    -0.90
     Canal
    -0.77
     Tolkien
    -0.75
    Tour
    -0.73
     Dickens
    -0.73
     gren
    -0.72
     palp
    -0.72
     toile
    -0.71
    uscript
    -0.71
    giene
    -0.71
    POSITIVE LOGITS
     Intel
    1.95
     CPUs
    1.87
     Ryzen
    1.86
     Xeon
    1.84
    Intel
    1.78
     AMD
    1.77
     processors
    1.74
     chipset
    1.68
     processor
    1.64
     CPU
    1.63
    Activations Density 0.416%

    No Known Activations