© 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. 10040
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating location or source, and terms related to availability or accessibility

    oai_token-act-pair · gpt-3.5-turbo

    references to availability or access to items or services

    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
    acter
    -0.76
    acan
    -0.73
    igil
    -0.70
     mattered
    -0.70
     senseless
    -0.68
    ortunate
    -0.67
    iquette
    -0.67
    wolves
    -0.67
    itiveness
    -0.64
    icans
    -0.64
    POSITIVE LOGITS
     download
    1.25
     Downloads
    0.99
     PDF
    0.98
    download
    0.97
     downloadable
    0.96
     Kindle
    0.95
     Download
    0.92
     pdf
    0.92
     downloads
    0.91
     Adobe
    0.86
    Activations Density 0.124%

    No Known Activations