© 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. 720
    Prev
    Next
    INDEX
    Explanations

    authors and researchers associated with studies or papers

    oai_token-act-pair · gpt-3.5-turbo

    references to authors and their respective studies or papers

    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
     blat
    -0.61
     baff
    -0.60
    conservancy
    -0.60
    fw
    -0.58
     fundament
    -0.56
     slightest
    -0.56
     manag
    -0.55
     inconven
    -0.54
    FW
    -0.54
    atron
    -0.54
    POSITIVE LOGITS
    hesis
    0.90
    itatively
    0.85
    heses
    0.81
    Published
    0.78
    essors
    0.74
     thereof
    0.73
     Cosponsors
    0.72
    ournals
    0.71
    ,,
    0.68
     of
    0.68
    Activations Density 0.068%

    No Known Activations