© 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. 10-RES-JB
    11. 16041
    Prev
    Next
    INDEX
    Explanations

    computer code snippets

    oai_token-act-pair · gpt-3.5-turbo

    references to computer code or error messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compliment
    -0.78
     designs
    -0.69
     cartoons
    -0.68
    asha
    -0.65
     drafting
    -0.64
     drafts
    -0.63
     infographic
    -0.62
    ï¸ı
    -0.62
    rosse
    -0.62
    âĢ¢âĢ¢
    -0.62
    POSITIVE LOGITS
     000000
    1.29
     00000000
    1.16
     ERROR
    1.11
     0000
    1.06
    000000
    1.05
     fixme
    1.04
    00007
    1.02
     Error
    1.01
     ACPI
    1.00
    Disable
    0.99
    Activations Density 0.211%

    No Known Activations