© 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. 6-RES-JB
    11. 13604
    Prev
    Next
    INDEX
    Explanations

    financial data and statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable statistics and data related to financial or demographic information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stakes
    -0.60
    odon
    -0.54
    bots
    -0.54
     comr
    -0.54
     marqu
    -0.54
     pals
    -0.53
     partying
    -0.52
    arton
    -0.52
    eport
    -0.51
    quished
    -0.51
    POSITIVE LOGITS
     percent
    0.81
    %
    0.77
     apiece
    0.72
     fewer
    0.70
     total
    0.68
    57
    0.66
     additional
    0.65
     crore
    0.64
    58
    0.62
    %),
    0.62
    Activations Density 0.389%

    No Known Activations