© 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. 10-RES-JB
    11. 16519
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a diverse range of situations or opinions being represented by a large group

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "many."

    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
    aban
    -0.75
    anut
    -0.73
    ILA
    -0.67
    iggurat
    -0.67
    ibal
    -0.66
    vertisement
    -0.65
    abo
    -0.65
    agame
    -0.64
    anything
    -0.63
    acus
    -0.62
    POSITIVE LOGITS
     times
    1.08
     observers
    0.96
    body
    0.92
     facets
    0.92
     aspects
    0.92
     people
    0.90
     commentators
    0.89
     countries
    0.87
     jurisdictions
    0.87
     commenters
    0.86
    Activations Density 0.082%

    No Known Activations