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

    Neuronpedia

    Jacobian LensNEW
    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. 1911
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to computer hardware

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications related to computer processors and features

    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
    iquette
    -1.07
     BuzzFeed
    -0.82
     grate
    -0.79
     begg
    -0.79
     palp
    -0.78
     toile
    -0.77
     Yelp
    -0.75
     etiquette
    -0.75
     undercover
    -0.75
     volunt
    -0.74
    POSITIVE LOGITS
     GPUs
    1.76
     CPUs
    1.71
     GPU
    1.71
     GDDR
    1.55
     CPU
    1.53
     processors
    1.51
     chipset
    1.50
     AMD
    1.46
    CPU
    1.45
     processor
    1.45
    Activations Density 0.417%

    No Known Activations